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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     podía
    0.75
     эк
    0.75
     было
    0.71
     estimular
    0.70
    дца
    0.69
     выс
    0.69
     podían
    0.69
    ются
    0.68
     этого
    0.67
    yaxis
    0.66
    POSITIVE LOGITS
    涀
    0.87
    ab
    0.87
    आधी
    0.86
     rô
    0.79
    ou
    0.79
    篩
    0.79
     lọc
    0.78
    ين
    0.77
    २
    0.77
    ru
    0.76
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.