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

    Neuronpedia

    INDEX
    Explanations

    graphics processing units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Такие
    0.91
     Доб
    0.84
     Далее
    0.84
     acerca
    0.83
     Такой
    0.83
     городского
    0.82
     JPEG
    0.82
    ссий
    0.81
     física
    0.80
     При
    0.79
    POSITIVE LOGITS
    R
    1.05
    D
    1.05
    U
    0.99
    A
    0.97
    T
    0.95
    P
    0.95
    B
    0.93
    Y
    0.91
    DON
    0.89
    רה
    0.88
    Act Density 0.000%

    No Known Activations