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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and computations, particularly involving fractions and variables

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

    Mathematical expressions and fractions

    np_acts-logits-general · gemini-2.0-flash

    mathematical and programming expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    -0.64
    /}{
    -0.59
    +#+
    -0.59
     trên
    -0.55
    InjectAttribute
    -0.54
    TestBed
    -0.52
     Pat
    -0.50
     /
    -0.49
    ./
    -0.49
     Pick
    -0.49
    POSITIVE LOGITS
     Мексичка
    0.86
    IsContent
    0.71
     NSCoder
    0.63
     scolaires
    0.60
     مصرى
    0.60
     imprimée
    0.59
     myſelf
    0.59
    MigrationBuilder
    0.58
    efforts
    0.58
     poffible
    0.58
    Act Density 0.761%

    No Known Activations