INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.08
     TILE
    -0.08
     Tango
    -0.08
    ാഴ
    -0.08
     Mini
    -0.08
     lotto
    -0.07
     holiday
    -0.07
     bitcoin
    -0.07
    		↵↵
    -0.07
     Ogun
    -0.07
    POSITIVE LOGITS
     symmetrical
    0.12
     symmetry
    0.11
     symmetric
    0.09
    -horizontal
    0.08
     يب
    0.08
     waf
    0.08
     nicely
    0.08
    ilhar
    0.08
     hinged
    0.08
    -axis
    0.08
    Act Density 0.016%

    No Known Activations