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

    Neuronpedia

    INDEX
    Explanations

    questions and suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #+#
    -0.98
    XmlAccessType
    -0.92
     nahilalakip
    -0.90
     חיצוניים
    -0.79
    انيف
    -0.78
     وتسجيلات
    -0.73
     Мексичка
    -0.66
    WebServlet
    -0.66
     الحره
    -0.66
    HasForeignKey
    -0.64
    POSITIVE LOGITS
     of
    0.66
     the
    0.55
    in
    0.54
     everything
    0.54
    le
    0.52
     that
    0.50
    on
    0.49
    lem
    0.48
    ľ
    0.48
    Inflater
    0.48
    Act Density 0.112%

    No Known Activations