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

    Neuronpedia

    INDEX
    Explanations

    possessive apostrophes and single quotation marks, and also numbers

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.88
    SharedDtor
    -0.88
     ویکی‌پدی
    -0.87
     Италијани
    -0.82
     ModelExpression
    -0.80
     '\\;'
    -0.79
     disambiguazione
    -0.78
    SharedCtor
    -0.78
     للاسماء
    -0.66
     <=",
    -0.64
    POSITIVE LOGITS
    twimg
    0.50
    lemény
    0.49
     kufanya
    0.48
    ngiliz
    0.48
     pflegen
    0.47
     Tennyson
    0.47
     NgModule
    0.47
    hradun
    0.46
     isolates
    0.46
    lope
    0.46
    Act Density 0.619%

    No Known Activations