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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    或许
    -0.08
    不屑
    -0.07
     vielleicht
    -0.07
    pics
    -0.07
     entender
    -0.07
    Misc
    -0.06
     anticipation
    -0.06
     ساع
    -0.06
     lacks
    -0.06
     spilled
    -0.06
    POSITIVE LOGITS
    国王
    0.07
    公认
    0.07
     Lama
    0.07
    setFlash
    0.07
     NSLog
    0.07
     astronomy
    0.07
     günü
    0.07
    磋商
    0.07
    تحد
    0.06
    汇报
    0.06
    Act Density 0.003%

    No Known Activations