INDEX
    Explanations

    automotive parts and accessories

    New Auto-Interp
    Negative Logits
     people
    -0.35
    Genre
    -0.33
     agences
    -0.32
    efe
    -0.32
     fe
    -0.30
     utafitiHapana
    -0.29
     prí
    -0.29
     effort
    -0.29
     allmän
    -0.29
     altså
    -0.28
    POSITIVE LOGITS
    WebElementEntity
    0.70
     autorytatywna
    0.63
    __*/
    0.60
     Numerade
    0.60
     للمعارف
    0.59
     stiffer
    0.57
    useNewUrlParser
    0.57
    WritableDatabase
    0.55
     mxArray
    0.52
     replaced
    0.51
    Act Density 0.016%

    No Known Activations