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

    Neuronpedia

    INDEX
    Explanations

    special character sequences and formatting patterns within the text

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

    numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     before
    -0.36
     for
    -0.34
    -
    -0.32
    k
    -0.30
    -0.30
    колко
    -0.30
     by
    -0.30
    wapV
    -0.30
    tahankan
    -0.30
     to
    -0.30
    POSITIVE LOGITS
     tartalomajánló
    0.65
    GIVEREF
    0.64
     ویکی‌پدی
    0.64
    TagMode
    0.60
    SharedDtor
    0.60
     EnglishChoose
    0.59
     للاسماء
    0.57
     مشين
    0.56
     виправивши
    0.56
     ErrIntOverflow
    0.56
    Act Density 0.120%
    No Known Activations