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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Його
    -0.07
     بو
    -0.07
     ніж
    -0.07
     прий
    -0.06
    StreamWriter
    -0.06
     Nie
    -0.06
    žení
    -0.06
    аного
    -0.06
    >You
    -0.06
    を見る
    -0.06
    POSITIVE LOGITS
    遠
    0.06
    ponsor
    0.06
     Malone
    0.06
     Comfort
    0.06
     ном
    0.06
     Pussy
    0.06
    icense
    0.06
    rolled
    0.06
     Av
    0.06
    out
    0.06
    Act Density 0.013%

    No Known Activations