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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    م
    0.59
    s
    0.57
    м
    0.55
    ม
    0.51
     Emails
    0.50
     Drapeau
    0.50
    ক
    0.48
     Emperors
    0.46
     Kamera
    0.45
     Mitochond
    0.45
    POSITIVE LOGITS
     سر
    0.50
     हिंसा
    0.50
    стройство
    0.50
    UGH
    0.48
    派
    0.48
     dangerous
    0.47
    خدام
    0.47
    Danger
    0.46
     sổ
    0.46
     compulsion
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.