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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting in code

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

    Go program imports or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.48
    windowFixed
    -0.40
     vedea
    -0.40
    writeValue
    -0.40
    beelden
    -0.38
    XIM
    -0.38
    Становништво
    -0.37
    ambut
    -0.37
    дивиду
    -0.37
    venuto
    -0.36
    POSITIVE LOGITS
     بيها
    0.55
    PyExc
    0.51
     clés
    0.47
    saraba
    0.47
     NSCoder
    0.46
     clef
    0.46
    testify
    0.46
    UrlResolution
    0.45
    EDEFAULT
    0.45
    richTextPanel
    0.43
    Act Density 0.000%

    No Known Activations