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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    一
    0.78
    現
    0.74
    明確
    0.70
    我
    0.68
    שות
    0.67
    私が
    0.67
    被
    0.67
    洗い
    0.66
    利用
    0.66
    見
    0.66
    POSITIVE LOGITS
     +,
    1.07
     (,
    1.03
     respir
    0.97
     fame
    0.97
     sécur
    0.95
     miglior
    0.94
     ofrecer
    0.92
     ),
    0.92
     filtre
    0.92
    <unused2169>
    0.91
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.