INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     #{
    -0.07
     stole
    -0.07
    Conta
    -0.07
     střed
    -0.07
     Coordinate
    -0.06
    _kses
    -0.06
    -0.06
    Servlet
    -0.06
     servlet
    -0.06
     Allen
    -0.06
    POSITIVE LOGITS
     lazy
    0.07
    YS
    0.07
    unders
    0.07
    аж
    0.07
     maxY
    0.06
     Wait
    0.06
    ":-
    0.06
     Lucky
    0.06
     injuries
    0.06
    Y
    0.06
    Act Density 0.002%

    No Known Activations