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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or structural elements in a document

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

    Tokens enclosed in parentheses

    np_acts-logits-general · gemini-2.0-flash

    dates, titles, and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enderror
    -0.87
     typelib
    -0.86
     isComment
    -0.85
    RegressionTest
    -0.84
    تقاوى
    -0.84
    ModelAdmin
    -0.83
     ProtoMessage
    -0.81
    webElementXpaths
    -0.80
    +#+#
    -0.78
     дописавши
    -0.78
    POSITIVE LOGITS
     
    1.00
     www
    0.80
     July
    0.77
     April
    0.75
     November
    0.75
     United
    0.74
     September
    0.73
     October
    0.71
     The
    0.71
     June
    0.71
    Act Density 0.973%

    No Known Activations