NeuroCogMap Reveals Cognitive Organization of Large Language Models

Hugging Face Daily Papers Papers
cognitive-science llm neuroscience interpretability framework representation

Summary

NeuroCogMap is a cognitive neuroscience-inspired framework that maps the internal features of large language models into functional parcels, linking them to interpretable cognitive functions and revealing signatures of model failures like hallucination and bias.

Understanding how complex cognitive functions are organized within artificial systems is central to interpreting large language models (LLMs) and relating them to biological cognition. Yet although LLMs exhibit broad cognitive-like behaviours, it remains unclear whether their internal representations form reproducible functional systems that explain behaviour, failure and links to human cognition. Here we present NeuroCogMap, a cognitive neuroscience-inspired framework that organizes internal features of LLMs into functional parcels and links them to interpretable functions, cognitive capabilities and a cognitive hierarchy. These parcels form a stable and semantically coherent organization that is partly conserved across models and functionally linked to model outputs. Within this organization, major LLM failures, including hallucination, bias, refusal failure and sycophancy, correspond to distinct disruptions in representational and behavioural-control systems, yielding internal signatures for mechanism-guided detection and targeted intervention. Beyond model behaviour, NeuroCogMap improves prediction of human cortical responses during naturalistic language comprehension, with the strongest correspondence in higher-order association cortex. At the cognitive level, its internal signatures expose latent strategies that guide refinements of classical models of human decision-making. Together, these findings establish NeuroCogMap as a system-level framework for mapping functional organization in artificial systems and for relating this organization to human cortical function and cognitive behaviour.
Original Article
View Cached Full Text

Cached at: 07/14/26, 04:13 AM

Paper page - NeuroCogMap Reveals Cognitive Organization of Large Language Models

Source: https://huggingface.co/papers/2607.00397 Published on Jul 1

·

Submitted byhttps://huggingface.co/Jeryi

SunZXon Jul 14

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Understandinghowcomplexcognitivefunctionsareorganizedwithinartificialsystemsiscentraltointerpretinglargelanguagemodels(LLMs)andrelatingthemtobiologicalcognition.YetalthoughLLMsexhibitbroadcognitive-likebehaviours,itremainsunclearwhethertheirinternalrepresentationsformreproduciblefunctionalsystemsthatexplainbehaviour,failureandlinkstohumancognition.HerewepresentNeuroCogMap,acognitiveneuroscience-inspiredframeworkthatorganizesinternalfeaturesofLLMsintofunctionalparcelsandlinksthemtointerpretablefunctions,cognitivecapabilitiesandacognitivehierarchy.Theseparcelsformastableandsemanticallycoherentorganizationthatispartlyconservedacrossmodelsandfunctionallylinkedtomodeloutputs.Withinthisorganization,majorLLMfailures,includinghallucination,bias,refusalfailureandsycophancy,correspondtodistinctdisruptionsinrepresentationalandbehavioural-controlsystems,yieldinginternalsignaturesformechanism-guideddetectionandtargetedintervention.Beyondmodelbehaviour,NeuroCogMapimprovespredictionofhumancorticalresponsesduringnaturalisticlanguagecomprehension,withthestrongestcorrespondenceinhigher-orderassociationcortex.Atthecognitivelevel,itsinternalsignaturesexposelatentstrategiesthatguiderefinementsofclassicalmodelsofhumandecision-making.Together,thesefindingsestablishNeuroCogMapasasystem-levelframeworkformappingfunctionalorganizationinartificialsystemsandforrelatingthisorganizationtohumancorticalfunctionandcognitivebehaviour.

View arXiv pageView PDFProject pageAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.00397 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.00397 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.00397 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Modular Cognitive Architecture Emerges in Large Language Models

arXiv cs.AI

This paper investigates whether modular cognitive architecture emerges in large language models, finding that LLMs develop specialized neural networks mirroring human brain organization across cognitive domains, suggesting modularity is a fundamental property of intelligent systems.

Heterogeneous Neural Predictivity from Language Models During Naturalistic Comprehension

arXiv cs.CL

This paper investigates how language model representations predict neural activity during naturalistic language comprehension across MEG, ECoG, and other recordings. The findings demonstrate that language model features serve as useful neural predictors, but caution against overinterpreting predictive success as evidence for shared neural organization.

Decomposing and Steering Functional Metacognition in Large Language Models

arXiv cs.CL

This research paper investigates functional metacognition in Large Language Models, demonstrating that internal states like evaluation awareness and self-assessed capability are linearly decodable from residual stream activations. The authors propose a mechanistic framework to steer these states, showing causal control over reasoning behaviors, verbosity, and safety responses.