Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     thickness
    1.04
     duration
    0.97
     thicknesses
    0.97
     muncul
    0.89
     saka
    0.87
    mouseX
    0.86
     multiplication
    0.84
     caracteriza
    0.83
     fullness
    0.82
     thick
    0.81
    POSITIVE LOGITS
    where
    0.77
    units
    0.76
    -
    0.74
    ball
    0.72
    .).
    0.70
    house
    0.70
    irie
    0.69
    fs
    0.69
    enta
    0.68
    .)
    0.67
    Act Density 0.000%

    No Known Activations