INDEX
    Explanations

    Locations and nationalities

    New Auto-Interp
    Negative Logits
    IES
    -0.59
    <bos>
    -0.54
    املة
    -0.54
     stanno
    -0.50
    hel
    -0.49
    ies
    -0.48
    H
    -0.48
    le
    -0.47
    hau
    -0.47
    ENED
    -0.47
    POSITIVE LOGITS
    تقاوى
    0.94
     виправивши
    0.84
    RenderAtEndOf
    0.84
     فريبيس
    0.78
    +#+#
    0.73
     дописавши
    0.73
    WindowConstants
    0.67
     resourceCulture
    0.67
    :✨
    0.66
    abestanden
    0.65
    Act Density 0.035%

    No Known Activations