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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     efek
    0.88
    gevity
    0.76
     жизни
    0.72
    ußen
    0.71
    ский
    0.71
    订阅
    0.70
    nesday
    0.69
     añad
    0.68
    kast
    0.68
    steroidal
    0.68
    POSITIVE LOGITS
    ا
    1.05
    تين
    0.82
     Logging
    0.81
    ل
    0.80
     You
    0.79
     Vous
    0.79
     Doesn
    0.79
     น่า
    0.78
     Posting
    0.78
    سمبر
    0.78
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.