INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ule
    -0.09
     AX
    -0.08
     adb
    -0.08
    ulem
    -0.08
    -0.08
     المك
    -0.07
     dx
    -0.07
     mk
    -0.07
     المع
    -0.07
     mt
    -0.07
    POSITIVE LOGITS
    0.08
     Pou
    0.08
    izia
    0.08
     pou
    0.08
    Pou
    0.07
     fingers
    0.07
    Basics
    0.07
     ferro
    0.07
     Koop
    0.07
    427
    0.07
    Act Density 0.027%

    No Known Activations