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

    Neuronpedia

    INDEX
    Explanations

    function definitions and variable assignments in code

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

    Non-English words or code snippets

    np_acts-logits-general · gemini-2.0-flash

    guanxing, ijiAsk, fenyong, tianxiang

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.66
     Wikiseite
    -0.65
    TagHelper
    -0.64
     متعلقه
    -0.62
     виправивши
    -0.57
     ویکی‌پدیا
    -0.56
     سكانية
    -0.54
    énario
    -0.54
    فایل‌لار
    -0.52
    wiście
    -0.51
    POSITIVE LOGITS
    *}[
    0.61
     przeci
    0.54
    viva
    0.54
    arraycopy
    0.52
    paramref
    0.51
     Armas
    0.51
    corbic
    0.49
     thiệu
    0.49
     kuş
    0.49
    agaimana
    0.48
    Act Density 0.161%

    No Known Activations