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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    i
    0.86
    ：
    0.80
    }\
    0.76
    ape
    0.75
     if
    0.71
     is
    0.70
    }_{
    0.70
    uther
    0.69
    acido
    0.69
    up
    0.69
    POSITIVE LOGITS
     هەر
    0.85
     przestr
    0.82
     espaces
    0.81
     切り
    0.78
     început
    0.77
     módulos
    0.76
     éta
    0.75
     zależności
    0.75
    镟
    0.75
     pelaksanaan
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.