INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     sent
    0.72
     prognostic
    0.68
     strategic
    0.67
     spider
    0.65
     bad
    0.65
     scipy
    0.63
     Monte
    0.63
    __
    0.63
     silk
    0.61
     Web
    0.61
    POSITIVE LOGITS
    kotlin
    1.87
    Kotlin
    1.81
     Kotlin
    1.68
     kotlin
    1.66
     println
    1.51
     kotlinx
    1.46
    println
    1.41
     listOf
    1.27
    ktx
    1.23
     arrayOf
    1.22
    Act Density 0.034%

    No Known Activations