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

    Neuronpedia

    INDEX
    Explanations

    percentage of the time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skjer
    -0.08
    ahanan
    -0.08
     sounding
    -0.08
     Grave
    -0.08
     القي
    -0.08
     חיים
    -0.08
    styr
    -0.07
    വ്
    -0.07
     vý
    -0.07
     القدرة
    -0.07
    POSITIVE LOGITS
    icamente
    0.09
    ifrån
    0.09
     veces
    0.09
    ратно
    0.09
     kerran
    0.09
    istically
    0.08
     ๆ
    0.08
     allá
    0.08
    రకు
    0.08
    적으로
    0.08
    Act Density 0.395%

    No Known Activations