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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ½
    0.61
    0.55
     ½
    0.55
     not
    0.54
    not
    0.54
     nuestro
    0.50
    全世界
    0.48
    เท่านั้น
    0.48
     fenced
    0.47
     нашего
    0.47
    POSITIVE LOGITS
    <unused2184>
    0.77
    uatan
    0.75
     Biraz
    0.75
    <unused2179>
    0.75
    <unused2123>
    0.75
    ጺ
    0.73
    <unused2176>
    0.71
     Ambris
    0.70
     Kalyan
    0.70
     Drav
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.