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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    SW
    0.58
    操
    0.58
    Activity
    0.57
    MeToo
    0.56
    System
    0.55
    ANT
    0.55
    US
    0.54
    処理
    0.54
    女
    0.54
    scope
    0.53
    POSITIVE LOGITS
     diversos
    0.99
     berbagai
    0.94
     различных
    0.94
     various
    0.91
     различными
    0.88
     diversas
    0.87
     varying
    0.85
     ವಿವಿಧ
    0.82
     diverses
    0.81
     différentes
    0.79
    Act Density 0.000%

    No Known Activations