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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurement or quantity

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

    numbers followed by punctuation or other numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.78
    oa̍t
    -0.73
    BASEPATH
    -0.71
     تضيفلها
    -0.65
     ligiloj
    -0.65
    tinyos
    -0.63
     AttributeSet
    -0.61
     BoxFit
    -0.61
    原始内容存档于
    -0.61
    ConstraintMaker
    -0.60
    POSITIVE LOGITS
     questions
    0.35
     segi
    0.34
    IV
    0.34
    кур
    0.31
     rosse
    0.30
     dedans
    0.30
    uncu
    0.30
     Bitte
    0.29
    uestions
    0.28
    uvres
    0.28
    Act Density 0.096%

    No Known Activations