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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     zodat
    0.84
     deporte
    0.83
    houettes
    0.82
    蟀
    0.82
     montañas
    0.79
    wski
    0.79
     watercolor
    0.78
    激发
    0.77
    縞
    0.76
    rometry
    0.76
    POSITIVE LOGITS
     இதை
    0.68
    However
    0.64
     라는
    0.64
    दास
    0.64
     ECONOMIC
    0.63
    एच
    0.63
     worried
    0.62
    следова
    0.62
     ملین
    0.62
    This
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.