INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Ceiling
    -0.12
     ceiling
    -0.10
     компен
    -0.10
     Walls
    -0.09
    ériel
    -0.09
     ceilings
    -0.09
    cija
    -0.09
    ceil
    -0.09
    enspiel
    -0.09
     recuper
    -0.09
    POSITIVE LOGITS
    0.26
    0.19
    0.17
    0.15
    [f
    0.15
    (f
    0.13
    =f
    0.11
     [
    0.11
    fl
    0.11
     ફ્લ
    0.11
    Act Density 0.027%

    No Known Activations