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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical symbols or operators

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

    positive numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stateProvider
    -0.52
    SharedDtor
    -0.49
     ویکی‌پدی
    -0.48
    IntoConstraints
    -0.48
     itinéraires
    -0.47
    MeasureSpec
    -0.46
    ⓧ
    -0.42
    SharedCtor
    -0.40
     initComponents
    -0.39
    AndEndTag
    -0.37
    POSITIVE LOGITS
     $+
    0.65
     (+
    0.64
    ">+
    0.62
     [+
    0.59
     +
    0.58
    (+
    0.57
     "+
    0.57
     +(
    0.57
     "+"
    0.56
    ("+
    0.55
    Act Density 0.003%

    No Known Activations