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

    Neuronpedia

    INDEX
    Explanations

    data assignments and operations in code

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

    Code and math symbols

    np_acts-logits-general · gemini-2.0-flash

    variable assignments and code execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    umna
    -0.52
    https
    -0.50
     مرئيه
    -0.48
     HttpHeaders
    -0.46
    InlineData
    -0.46
     brooms
    -0.46
    GitHub
    -0.46
     PLOS
    -0.46
     GitHub
    -0.45
     Colla
    -0.45
    POSITIVE LOGITS
     ExecuteAsync
    0.97
    GEBURTSDATUM
    0.78
    (!__
    0.76
    IsMutable
    0.68
    findpost
    0.66
     ModelExpression
    0.66
    ReusableCell
    0.63
     Paglinawan
    0.63
    はじめに
    0.62
     }}$}
    0.61
    Act Density 0.063%

    No Known Activations