INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     fason
    -0.08
    	sc
    -0.07
     Rasmussen
    -0.07
     arquivo
    -0.07
     Estes
    -0.07
     photon
    -0.07
     exc
    -0.07
    教師
    -0.06
     bhfuil
    -0.06
     atributos
    -0.06
    POSITIVE LOGITS
     panor
    0.10
     panoramic
    0.09
    تيات
    0.09
     רח
    0.08
     darunter
    0.08
    Cheers
    0.08
     pracht
    0.08
    prüng
    0.08
     BOARD
    0.08
     east
    0.08
    Act Density 0.014%

    No Known Activations