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

    Neuronpedia

    INDEX
    Explanations

    specific programming terms and references to code libraries

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

    code and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.77
    <unused3>
    -0.73
    <unused43>
    -0.73
    <unused52>
    -0.73
    <unused23>
    -0.73
    <pad>
    -0.73
    <unused28>
    -0.73
    <unused51>
    -0.73
    <unused8>
    -0.73
    <unused16>
    -0.73
    POSITIVE LOGITS
    calientes
    0.46
    apimachinery
    0.44
    NSNumber
    0.38
    CellValue
    0.33
    riwal
    0.31
    fromCharCode
    0.31
    sopp
    0.30
     custom
    0.30
     bağlı
    0.28
    StatusCodes
    0.28
    Act Density 0.007%

    No Known Activations