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

    Neuronpedia

    INDEX
    Explanations

    offset

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     روسی
    -0.07
     týden
    -0.06
    asco
    -0.06
    ние
    -0.06
    щини
    -0.06
     národ
    -0.06
     Bulletin
    -0.06
    control
    -0.06
     yesterday
    -0.06
     Daly
    -0.06
    POSITIVE LOGITS
    ٨
    0.07
    534
    0.06
    ۲۳
    0.06
    .al
    0.06
     row
    0.06
    extend
    0.06
    [src
    0.06
    ٢
    0.06
    .usuario
    0.06
     drift
    0.06
    Act Density 0.012%

    No Known Activations