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

    Neuronpedia

    INDEX
    Explanations

    the starting point of the document, indicating the beginning of a new piece of text

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

    after a symbol or punctuation

    np_acts-logits-general · gemini-2.0-flash

    disrupt Philadelphia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "><?=
    -0.53
     '*':
    -0.53
     ${{
    -0.53
    telser
    -0.53
    <?
    -0.53
     Stirn
    -0.52
    PasswordField
    -0.51
    𝟹
    -0.50
    cuma
    -0.50
    RatingBar
    -0.50
    POSITIVE LOGITS
    tvguidetime
    0.85
    TestingModule
    0.69
     nahilalakip
    0.69
     ویکی‌پدیا
    0.65
     ModelExpression
    0.65
    abestanden
    0.60
    yntaxException
    0.58
    TagMode
    0.58
    PRWEB
    0.56
    JvmStatic
    0.56
    Act Density 0.004%

    No Known Activations