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

    Neuronpedia

    INDEX
    Explanations

    code or notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     każdym
    -0.09
     సందర్భంగా
    -0.08
    ب
    -0.08
    omb
    -0.08
     zakresie
    -0.07
     Peters
    -0.07
     כגון
    -0.07
    బ
    -0.07
     Sax
    -0.07
     deede
    -0.07
    POSITIVE LOGITS
     cosas
    0.08
     traiter
    0.07
     открыть
    0.07
     кіль
    0.07
     считать
    0.07
    股
    0.07
    ouvrir
    0.07
    緒
    0.07
    ?)
    0.07
    ฤ
    0.07
    Act Density 0.017%

    No Known Activations