INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    212
    -0.08
    877
    -0.08
     nguy
    -0.08
    ANI
    -0.07
    iman
    -0.07
    todos
    -0.07
    Lastname
    -0.07
    )+"
    -0.07
    808
    -0.07
    450
    -0.07
    POSITIVE LOGITS
     dür
    0.08
     з
    0.07
     chodzi
    0.07
     играть
    0.07
     Internationale
    0.07
     работать
    0.07
    0.07
     Rud
    0.07
     Zert
    0.07
     certificate
    0.07
    Act Density 0.002%

    No Known Activations