INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ل
    0.83
    يا
    0.71
    л
    0.68
    Ве
    0.68
    0.67
    遺跡
    0.64
    नई
    0.63
    Под
    0.62
    0.62
    Во
    0.61
    POSITIVE LOGITS
    Hispanic
    0.92
     Hispanic
    0.87
     Hispanics
    0.76
     hispanic
    0.72
     Latinos
    0.71
     Latino
    0.68
    -
    0.60
     cancers
    0.59
     bruises
    0.58
    overty
    0.57
    Act Density 0.001%

    No Known Activations