INDEX
    Explanations

    shapes and containers

    New Auto-Interp
    Negative Logits
     siri
    -0.09
     cele
    -0.08
    Imm
    -0.07
     operation
    -0.07
    igur
    -0.07
     Have
    -0.07
     הק
    -0.07
    ustum
    -0.07
     מע
    -0.07
    finally
    -0.07
    POSITIVE LOGITS
     understandable
    0.09
    .Tile
    0.09
    _COUNT
    0.08
    нага
    0.08
    0.08
    _tiles
    0.08
    0.08
     nepiecieš
    0.08
     vreemde
    0.08
    0.08
    Act Density 0.056%

    No Known Activations