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

    Neuronpedia

    INDEX
    Explanations

    parameters and annotations typically found in programming or function documentation

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

    documentation tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.75
    tinyos
    -0.75
    uxxxx
    -0.73
    parsedMessage
    -0.66
     виправивши
    -0.63
    principalTable
    -0.60
     nakalista
    -0.59
    出版年
    -0.59
    oredCriteria
    -0.57
    nezeu
    -0.56
    POSITIVE LOGITS
    propTypes
    0.39
    bindValue
    0.39
     JADX
    0.35
    typen
    0.34
     konkre
    0.34
     gethan
    0.33
    ài
    0.33
     Humane
    0.33
     tắt
    0.33
    攝
    0.33
    Act Density 0.009%

    No Known Activations