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

    Neuronpedia

    INDEX
    Explanations

    phrases related to calculations and mathematical problems

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

    calculating derivatives, remainders, common multiples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.75
     betweenstory
    -0.65
    رشف
    -0.62
     مشين
    -0.62
    awtextra
    -0.60
    devamını
    -0.59
    oa̍t
    -0.59
     BrowserModule
    -0.56
     ویکی‌پدی
    -0.55
     Italijanski
    -0.55
    POSITIVE LOGITS
     the
    0.60
     maximum
    0.53
     minimum
    0.51
     effective
    0.50
     total
    0.49
     a
    0.47
     difference
    0.46
    有多少
    0.46
     The
    0.45
     fallu
    0.44
    Act Density 0.158%

    No Known Activations