INDEX
    Explanations

    references to family members, particularly mothers

    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.63
    -0.63
     TextInputType
    -0.62
     okuyayım
    -0.60
     Administrativna
    -0.59
    tvguidetime
    -0.59
    KommentareTeilen
    -0.59
     utafitiHapana
    -0.58
     متعلقه
    -0.54
     تانيه
    -0.53
    POSITIVE LOGITS
    انگلیسی
    0.66
     cómics
    0.61
     MatDialog
    0.61
    tubers
    0.58
    ául
    0.58
    labelledby
    0.56
     laikā
    0.56
    zzleHttp
    0.55
     NSObject
    0.55
    imageio
    0.54
    Act Density 0.205%

    No Known Activations