INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    1
    1.00
    0
    0.97
    ang
    0.94
    ak
    0.92
    0.89
    are
    0.87
    am
    0.86
    ból
    0.83
    on
    0.78
    ur
    0.75
    POSITIVE LOGITS
     drown
    1.14
     drowning
    1.10
    سی
    1.09
     drowned
    1.05
    یک
    0.97
    その
    0.95
    ین
    0.91
    یر
    0.90
    وسی
    0.82
    ری
    0.82
    Act Density 0.001%

    No Known Activations