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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    é
    0.88
    ou
    0.84
     für
    0.79
    er
    0.78
    imed
    0.76
     bliz
    0.75
    y
    0.73
     é
    0.73
     anni
    0.73
     startling
    0.72
    POSITIVE LOGITS
    如果不
    0.70
    ਾਰ
    0.69
    鯤
    0.68
    ផលិត
    0.67
    貔
    0.66
     Cabo
    0.65
    ្នក
    0.65
    楶
    0.65
    各
    0.64
     शिवराज
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.