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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    不過
    0.95
     fornece
    0.93
     desenvolver
    0.84
    醬
    0.83
     deles
    0.83
    sdale
    0.82
    gleich
    0.81
     Também
    0.80
     estabelecer
    0.80
    죠
    0.79
    POSITIVE LOGITS
     Exposure
    0.84
    ↵
    0.84
    Y
    0.80
    Coin
    0.75
    ن
    0.74
     Sending
    0.74
     On
    0.73
     Compass
    0.73
     Exposed
    0.72
    ب
    0.72
    Act Density 0.000%

    No Known Activations