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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    можно
    -0.07
     Все
    -0.07
    Sure
    -0.07
    available
    -0.07
    睽
    -0.07
     Additionally
    -0.07
    一阵
    -0.06
    quiz
    -0.06
    lite
    -0.06
    է
    -0.06
    POSITIVE LOGITS
    تحرير
    0.08
     homosexuals
    0.08
    および
    0.07
     tertiary
    0.07
     Direction
    0.07
     gj
    0.07
    的发生
    0.07
     Ar
    0.07
    進め
    0.06
     tractor
    0.06
    Act Density 0.001%

    No Known Activations