INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Button
    0.57
     Button
    0.54
     button
    0.54
    按钮
    0.52
     BUTTON
    0.52
    button
    0.51
    Key
    0.49
    0.47
     buttons
    0.46
    BUTTON
    0.45
    POSITIVE LOGITS
     Ctrl
    0.89
     ctrl
    0.82
     Shift
    0.80
    Ctrl
    0.79
     SPACE
    0.79
     ESC
    0.78
     Esc
    0.76
    ESC
    0.76
    ctrl
    0.75
     CTRL
    0.75
    Act Density 0.093%

    No Known Activations