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

    Neuronpedia

    INDEX
    Explanations

    the relationships between numerical values and their classifications or categories

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

    letter followed by closing parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.33
     navigu
    -0.31
     operadores
    -0.31
     PopupWindow
    -0.31
    KommentareTeilen
    -0.30
    لينكات
    -0.30
     समीक्षक
    -0.30
    といけない
    -0.30
    ::_('
    -0.30
     símbolo
    -0.30
    POSITIVE LOGITS
    twimg
    0.53
    urlpatterns
    0.52
     autorytatywna
    0.50
    AISSEE
    0.49
    culata
    0.48
     ujednoznacz
    0.47
    بوابة
    0.47
     NSCoder
    0.46
    Lähteet
    0.45
    Autoritní
    0.44
    Act Density 0.117%

    No Known Activations