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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting indicators

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

    References, citations, or footnotes

    np_acts-logits-general · gemini-2.0-flash

    numbers, punctuation, and type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تانيه
    -0.64
    DrawerToggle
    -0.59
    TintMode
    -0.58
    出版年
    -0.56
     الاطلاع
    -0.51
    oplayer
    -0.50
    ddots
    -0.49
    Spoljašnje
    -0.49
     varargin
    -0.49
     [+
    -0.49
    POSITIVE LOGITS
     termica
    0.67
    lgari
    0.59
     natale
    0.59
     StatefulWidget
    0.59
     vectorielle
    0.58
    TextHelper
    0.57
    copyFrom
    0.57
     anzunehmen
    0.56
    mtd
    0.55
    一身
    0.55
    Act Density 0.134%

    No Known Activations