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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    粹
    0.76
     ვერ
    0.73
     bottlenecks
    0.71
    ד
    0.70
     istot
    0.70
     України
    0.68
     $$\
    0.65
     $=\
    0.64
    ད
    0.64
    দ
    0.63
    POSITIVE LOGITS
    ्ट
    0.86
    are
    0.84
    tion
    0.82
    рые
    0.82
    till
    0.81
    ры
    0.81
    娘
    0.80
    ị
    0.79
    tól
    0.77
    maker
    0.77
    Act Density 0.000%

    No Known Activations