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

    Neuronpedia

    INDEX
    Explanations

    repeated punctuation, particularly periods

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

    math and code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijani
    -0.73
     ModelExpression
    -0.72
    ArgsConstructor
    -0.69
    delwed
    -0.69
    Datuak
    -0.69
    elemField
    -0.66
    Vidite
    -0.66
     Biôgrafia
    -0.66
    QMetaType
    -0.65
     nakalista
    -0.65
    POSITIVE LOGITS
    元
    0.41
    PHeader
    0.35
    之
    0.35
    fwd
    0.34
    pptx
    0.34
    docx
    0.33
     Lä
    0.33
    港
    0.33
    ícola
    0.33
    png
    0.32
    Act Density 0.170%

    No Known Activations