INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    idan
    -0.70
     absolute
    -0.53
     Mills
    -0.52
     sportivo
    -0.50
    aten
    -0.48
     sheltered
    -0.47
     vostro
    -0.44
     M
    -0.43
    iri
    -0.43
    viks
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.81
     يتيمه
    0.78
    AndEndTag
    0.76
    TestBed
    0.75
    addCriterion
    0.75
     esternos
    0.73
    enfone
    0.72
    InputTagHelper
    0.71
    ItemBackground
    0.71
     EClass
    0.70
    Act Density 0.544%

    No Known Activations