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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     safes
    0.73
     regal
    0.72
     sofern
    0.71
     trades
    0.69
     stab
    0.69
     hands
    0.68
    示す
    0.68
     duplicate
    0.67
     result
    0.65
    شف
    0.65
    POSITIVE LOGITS
    lis
    0.92
     소
    0.81
    astus
    0.79
    arthen
    0.78
    ье
    0.77
    ні
    0.77
     रूम
    0.77
    ania
    0.75
     hadir
    0.74
     аў
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.