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

    Neuronpedia

    INDEX
    Explanations

    terms related to logical reasoning and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    only single or one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.67
    OGND
    -0.65
    postsleuth
    -0.57
    Personendaten
    -0.55
    EndContext
    -0.55
    InitStruct
    -0.54
    DockStyle
    -0.54
    adpleegd
    -0.53
    Попис
    -0.53
     protoimpl
    -0.53
    POSITIVE LOGITS
     degrees
    0.34
    balleur
    0.31
     reporta
    0.31
    Enums
    0.31
     determin
    0.30
    purge
    0.29
     master
    0.29
    enums
    0.28
     sklearn
    0.28
     détermin
    0.28
    Act Density 0.081%

    No Known Activations