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

    Neuronpedia

    INDEX
    Explanations

    phrases that reflect skepticism or doubt regarding claims or statements

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

    Criticism of opinions/claims

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by specific people or places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.03
    tagHelperRunner
    -0.95
    SourceChecksum
    -0.90
    RectangleBorder
    -0.87
     للاسماء
    -0.84
    OGND
    -0.83
     BoxDecoration
    -0.83
    ValueStyle
    -0.81
     Wikimedijinoj
    -0.81
    SharedCtor
    -0.80
    POSITIVE LOGITS
     "
    0.61
    なるほど
    0.56
    >
    0.54
     @
    0.53
     >
    0.53
    @
    0.52
    ướ
    0.52
     Bah
    0.48
     #
    0.48
    それにしても
    0.47
    Act Density 0.500%

    No Known Activations