INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Slate
    -0.15
     Dann
    -0.14
    kas
    -0.14
    /libs
    -0.14
    kle
    -0.14
    PHPExcel
    -0.13
     MR
    -0.13
     Sek
    -0.13
     Pdf
    -0.13
     slate
    -0.13
    POSITIVE LOGITS
     file
    0.30
     files
    0.29
    íĮĮìĿ¼
    0.29
    æĸĩä»¶
    0.28
     íĮĮìĿ¼
    0.25
     ÑĦайл
    0.24
    -file
    0.24
    -files
    0.23
    .gz
    0.22
    æł¼å¼ı
    0.21
    Act Density 0.065%

    No Known Activations