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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    zl
    -0.79
    bred
    -0.78
    esi
    -0.68
    ritical
    -0.66
     Nero
    -0.64
    âĿ
    -0.64
    Ont
    -0.62
     cardinal
    -0.62
     heavier
    -0.60
     pal
    -0.59
    POSITIVE LOGITS
    ifice
    0.75
    ophys
    0.72
     Mahjong
    0.71
    bang
    0.70
    vernment
    0.69
    remlin
    0.66
    puter
    0.64
     Kinect
    0.61
    ograph
    0.61
     mathemat
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.