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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ፥
    0.94
    t
    0.87
     ruin
    0.85
    ен
    0.83
     rags
    0.80
     infidelity
    0.79
     rhyth
    0.78
    掃除
    0.78
     JK
    0.78
    mila
    0.78
    POSITIVE LOGITS
     بودند
    0.73
     través
    0.71
     vườn
    0.69
    |.
    0.68
    тери
    0.66
     خیر
    0.65
    дели
    0.65
    urik
    0.65
    なりません
    0.63
    urf
    0.62
    Act Density 0.000%

    No Known Activations