INDEX
    Explanations

    damage/breakage

    New Auto-Interp
    Negative Logits
    MLLoader
    -0.79
     AssemblyCompany
    -0.77
    ContentAsync
    -0.70
    blurRadius
    -0.63
    ue
    -0.62
    ftagPool
    -0.61
     חיצוניים
    -0.59
     SearchView
    -0.59
    makeText
    -0.59
    BagLayout
    -0.57
    POSITIVE LOGITS
    Географиясе
    0.53
    ../../
    0.53
     nakalista
    0.52
    ../../../
    0.47
    قایناق‌لار
    0.47
     Pues
    0.46
    etCode
    0.46
    θος
    0.44
     springfox
    0.44
    RAE
    0.43
    Act Density 0.203%

    No Known Activations