INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     gloss
    -0.08
    -0.08
     análise
    -0.07
     analyzed
    -0.07
     hira
    -0.07
    role
    -0.07
    	role
    -0.07
    بادل
    -0.07
     gum
    -0.07
     Kendall
    -0.07
    POSITIVE LOGITS
     trims
    0.11
     trimming
    0.10
     rectangular
    0.10
     cropping
    0.10
    .margin
    0.10
    .UTC
    0.09
    .Padding
    0.09
    Margins
    0.09
    0.09
    0.09
    Act Density 0.006%

    No Known Activations