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

    Neuronpedia

    INDEX
    Explanations

    references to models or model-related terminology

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

    identifiers from multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    richTextPanel
    -0.52
    queryInterface
    -0.47
    DockStyle
    -0.46
    setVerticalGroup
    -0.46
    MessageOf
    -0.44
    Kanpo
    -0.43
    Aholisi
    -0.41
     مشارکت‌کنندگان
    -0.41
    TemporalType
    -0.40
    cshtml
    -0.40
    POSITIVE LOGITS
    Билгалдахарш
    0.51
     poveznice
    0.48
     تكبرها
    0.48
    Hochspringen
    0.43
     Wikimedijinoj
    0.42
    __':
    0.41
     getItemId
    0.40
     EconPapers
    0.37
    jspb
    0.37
    __':
    0.36
    Act Density 0.000%

    No Known Activations