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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries related to reasoning and possibilities

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

    questions starting with why

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences or phrases that are asking a question (especially wh‑words like "why/what/how" and other interrogative phrasing).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     незавершена
    -1.01
     kasarigan
    -0.98
     otomatig
    -0.88
     للاسماء
    -0.87
    EDEFAULT
    -0.87
    WebElementEntity
    -0.85
     للمعارف
    -0.82
     Chwiliwch
    -0.82
    RenderAtEndOf
    -0.79
    adaptiveStyles
    -0.76
    POSITIVE LOGITS
     
    0.47
    /
    0.41
     Tan
    0.38
    la
    0.37
     (
    0.36
     ru
    0.36
     Ry
    0.36
    ↵
    0.36
    -
    0.35
    ru
    0.35
    Act Density 0.164%

    No Known Activations