INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    nltk
    0.47
    lubridate
    0.44
     formalities
    0.44
     мероприятий
    0.44
    archiw
    0.44
    কমার
    0.43
    0.43
    getcwd
    0.43
    managing
    0.43
    statements
    0.43
    POSITIVE LOGITS
     shader
    1.15
     texture
    1.14
     textures
    1.05
     Texture
    1.01
     Shader
    0.99
     shaders
    0.97
    Texture
    0.95
     pixel
    0.89
    Shader
    0.89
     blending
    0.86
    Act Density 0.059%

    No Known Activations