INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Cone
    -0.10
     EPA
    -0.09
     aponta
    -0.09
     Triangle
    -0.09
    Cone
    -0.09
     cone
    -0.09
    _triangle
    -0.08
     Outreach
    -0.08
    pakken
    -0.08
     Arc
    -0.08
    POSITIVE LOGITS
     grid
    0.26
    grid
    0.23
    Grid
    0.22
    (grid
    0.22
    .grid
    0.21
    _grid
    0.21
    	grid
    0.21
    -grid
    0.21
     grids
    0.20
    _GRID
    0.19
    Act Density 0.065%

    No Known Activations