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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     hypersurface
    0.85
     instill
    0.80
     ruthenium
    0.78
     thứ
    0.77
     hydrocarbon
    0.77
     ambulance
    0.76
     hypersurfaces
    0.76
     erase
    0.75
     restructure
    0.75
     induce
    0.74
    POSITIVE LOGITS
    n
    0.93
    ن
    0.93
    н
    0.91
    ص
    0.79
    ل
    0.77
    L
    0.75
    ش
    0.75
    صور
    0.71
    M
    0.71
    تميز
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.