INDEX
    Explanations

    linear equations

    New Auto-Interp
    Negative Logits
    _SPI
    -0.08
     сфер
    -0.07
    .spy
    -0.07
    ajari
    -0.07
    pr
    -0.07
     explosion
    -0.07
    .wicket
    -0.07
    prest
    -0.07
     विर
    -0.07
    .elasticsearch
    -0.07
    POSITIVE LOGITS
     linear
    0.14
     Linear
    0.13
     лин
    0.12
    Linear
    0.11
    linear
    0.11
    .linear
    0.11
    _linear
    0.10
    -linear
    0.10
     lini
    0.10
     slope
    0.08
    Act Density 0.121%

    No Known Activations