INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     entreg
    -0.07
    _DB
    -0.06
    (btn
    -0.06
     comboBox
    -0.06
    PUBLIC
    -0.06
    Insets
    -0.06
     посл
    -0.06
     cheek
    -0.06
    umble
    -0.06
    oma
    -0.06
    POSITIVE LOGITS
    .imageUrl
    0.07
     perspectives
    0.07
    Pipeline
    0.06
     guarantees
    0.06
     Filip
    0.06
     awhile
    0.06
     dwelling
    0.06
     roční
    0.06
    -upload
    0.06
     glitches
    0.06
    Act Density 0.007%

    No Known Activations