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

    Neuronpedia

    INDEX
    Explanations

    references to specific statistics and categories in a given context

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

    names and references related to individuals, particularly those in the arts and public life

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

    English/French/Spanish/Korean language or sports categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.73
    ConstraintMaker
    -0.71
    AndEndTag
    -0.70
    AntiForgeryToken
    -0.68
     <=",
    -0.63
    ыгана
    -0.62
    ISupport
    -0.60
    ViewFeatures
    -0.60
     مرئيه
    -0.59
    Източници
    -0.59
    POSITIVE LOGITS
    _(
    0.75
    disambiguation
    0.74
     Вікіпе
    0.67
    _%
    0.63
    曖昧さ回避
    0.63
    列表
    0.61
    ⓘ
    0.60
     Wikipedia
    0.59
    を参照
    0.58
     목록
    0.57
    Act Density 0.280%

    No Known Activations