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

    Neuronpedia

    INDEX
    Explanations

    Queen Elizabeth, Jubilees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    自然是
    -0.08
     warehouses
    -0.07
    西安
    -0.07
     помещ
    -0.07
    (Element
    -0.07
    .Card
    -0.07
    帻
    -0.07
    <User
    -0.07
    찎
    -0.07
    :Object
    -0.07
    POSITIVE LOGITS
    (one
    0.08
     OCT
    0.07
    骂
    0.07
     Horny
    0.07
    IH
    0.07
    lagen
    0.07
    ição
    0.07
    מאה
    0.06
     dopamine
    0.06
    valuation
    0.06
    Act Density 0.008%

    No Known Activations