INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ditor
    -0.11
     Navigator
    -0.09
     pinch
    -0.09
    Navigation
    -0.09
     Navigation
    -0.09
     tabs
    -0.09
    ibu
    -0.09
     propaganda
    -0.08
    رÛĮÙģ
    -0.08
    .Navigation
    -0.08
    POSITIVE LOGITS
     pop
    0.15
     notification
    0.15
     icon
    0.15
     tray
    0.15
     Tray
    0.14
     Toast
    0.14
     toaster
    0.14
     dismiss
    0.14
     Notification
    0.13
     toast
    0.13
    Act Density 0.053%

    No Known Activations