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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cuna
    0.94
    砦
    0.93
     Gadd
    0.91
     Mullen
    0.90
     agus
    0.88
    cier
    0.88
     Trafford
    0.88
    鹕
    0.86
     Pennington
    0.86
    ี้
    0.86
    POSITIVE LOGITS
     Japan
    2.46
    Japan
    2.43
    Japanese
    2.41
     Japanese
    2.37
     Япо
    2.33
     japan
    2.32
     Japon
    2.31
     jap
    2.29
     япон
    2.28
    ญี่ปุ่น
    2.27
    Act Density 1.200%

    No Known Activations