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

    Neuronpedia

    INDEX
    Explanations

    expressions of approval or agreement

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

    short affirmative responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.30
    السكان
    -0.23
     typelib
    -0.23
     /\.
    -0.23
     spese
    -0.23
    Vidite
    -0.22
     boste
    -0.21
    共
    -0.21
     Stages
    -0.21
     εφ
    -0.21
    POSITIVE LOGITS
     nakalista
    0.72
    IVEREF
    0.71
    TestingModule
    0.69
    الحياه
    0.66
    lanatory
    0.65
     فريبيس
    0.64
     yyb
    0.63
    Haha
    0.63
    Hahaha
    0.59
     autorytatywna
    0.57
    Act Density 0.198%

    No Known Activations