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

    Neuronpedia

    INDEX
    Explanations

    code-related constructs and functions in programming

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

    Code, comments, or non-English words

    np_acts-logits-general · gemini-2.0-flash

    java and javascript code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Портал
    -0.61
    Portale
    -0.52
    endor
    -0.46
    ush
    -0.46
    urllib
    -0.44
    moveToFirst
    -0.44
    portál
    -0.44
    僕も
    -0.44
    ]['
    -0.44
    igné
    -0.44
    POSITIVE LOGITS
     بيها
    0.78
     للاسماء
    0.76
     */
    0.73
     propOrder
    0.73
     *
    0.70
     EconPapers
    0.66
     ProtoMessage
    0.66
    Personensuche
    0.65
    ]")]
    0.63
     insuffisamment
    0.62
    Act Density 0.032%

    No Known Activations