Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical AblationJan 1, 2026·Francesco SovranoGabriele DominiciMarc Langheinrich· 0 min read URL Cite DOITypeJournal articlePublicationCoRRpublicationsLast updated on Jan 1, 2026 AuthorsFrancesco SovranoPostdocGabriele DominiciPhD StudentMarc LangheinrichProfessor← Multi-modal physiological markers of arousal induced by CO2 inhalation in Virtual Reality Jan 1, 2026Platform and Study Design for Adaptive EMA Using Smart Glasses to Monitor Affective States Jan 1, 2026 →
