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

    Neuronpedia

    INDEX
    Explanations

    phrases or symbols indicative of mathematical operations or expressions

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

    latex math environments and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caza
    -0.35
     proprement
    -0.34
     clás
    -0.33
     sociala
    -0.32
    เศ
    -0.31
     crimen
    -0.28
    足够的
    -0.28
     celle
    -0.28
     aspet
    -0.28
     ihop
    -0.28
    POSITIVE LOGITS
     resourceCulture
    0.74
     Wikimedijinoj
    0.73
     ویکی‌آمباردا
    0.71
     HasFactory
    0.69
     propOrder
    0.66
     المعيارى
    0.65
    IntoConstraints
    0.64
     виправивши
    0.62
    ArrowToggle
    0.61
    Personensuche
    0.61
    Act Density 1.213%

    No Known Activations