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

    Neuronpedia

    INDEX
    Explanations

    financial and statistical data regarding medical studies

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

    Numbers followed by percent signs and parenthesised counts

    np_acts-logits-general · gemini-2.0-flash

    numbers and text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.70
     defStyleAttr
    -0.56
    lode
    -0.54
     فريبيس
    -0.53
    AxisAlignment
    -0.53
    UserScript
    -0.52
    long
    -0.51
     long
    -0.50
     ***!
    -0.49
    MAIN
    -0.49
    POSITIVE LOGITS
     ModelExpression
    0.76
     للاسماء
    0.66
    kloped
    0.62
     سكانية
    0.60
    اديم
    0.58
    InjectAttribute
    0.57
    CommandText
    0.56
     quelques
    0.56
    Бахар
    0.56
    few
    0.56
    Act Density 0.374%

    No Known Activations