INDEX
    Explanations

    slavic names

    New Auto-Interp
    Negative Logits
    do
    -0.90
    ov
    -0.77
    Do
    -0.62
    sw
    -0.61
    dos
    -0.54
    sho
    -0.54
     latine
    -0.51
    íslu
    -0.49
     individuelle
    -0.49
    autonomie
    -0.48
    POSITIVE LOGITS
    AnimationsModule
    0.64
    anyahu
    0.60
    Enllaces
    0.60
    scalatest
    0.60
    onews
    0.58
    henge
    0.57
    ELESS
    0.57
    Izvori
    0.55
    avax
    0.54
    vella
    0.54
    Act Density 0.189%

    No Known Activations