INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.09
    sqrt
    -0.08
    fat
    -0.08
    mu
    -0.08
    lug
    -0.08
    cant
    -0.07
    antil
    -0.07
     collectors
    -0.07
     Willy
    -0.07
     spas
    -0.07
    POSITIVE LOGITS
     неизвест
    0.09
    Reflect
    0.09
     Nuit
    0.08
     UNKNOWN
    0.08
     Reflect
    0.08
     конструк
    0.08
     Boiler
    0.08
    Expire
    0.08
     reflecting
    0.08
     дана
    0.08
    Act Density 0.000%

    No Known Activations