Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    describing technical components and principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noch
    0.99
    bonus
    0.91
     bonus
    0.91
     nagging
    0.90
     uptick
    0.89
     afterthought
    0.89
     lingering
    0.88
     demoral
    0.85
     cynical
    0.85
     cautious
    0.85
    POSITIVE LOGITS
     Components
    1.42
    的基本
    1.30
     Principles
    1.22
     Characteristics
    1.21
    Components
    1.21
     Overview
    1.17
    Characteristics
    1.16
     主要
    1.16
     Composition
    1.15
     Architecture
    1.15
    Act Density 4.104%

    No Known Activations