INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     inhibit
    -0.06
     τ
    -0.06
    ENSIONS
    -0.06
    legate
    -0.06
     LOVE
    -0.06
     violated
    -0.06
     ISI
    -0.06
    -0.06
    _UNITS
    -0.05
     takeover
    -0.05
    POSITIVE LOGITS
     GestureDetector
    0.07
    .invoice
    0.07
    QPushButton
    0.07
     objekt
    0.06
     launcher
    0.06
    _spinner
    0.06
    ffield
    0.06
    .simpleButton
    0.06
     Tcl
    0.06
    plies
    0.06
    Act Density 0.020%

    No Known Activations