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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    認為
    -0.07
     lead
    -0.07
    腐蚀
    -0.07
    ك
    -0.07
     melt
    -0.06
    ╘
    -0.06
    �
    -0.06
    兒子
    -0.06
     diet
    -0.06
    ilt
    -0.06
    POSITIVE LOGITS
    鄭
    0.08
    iversal
    0.08
    รอบ
    0.08
     pharm
    0.07
    роме
    0.07
    western
    0.07
    _FACTORY
    0.07
    Hostname
    0.07
     donation
    0.07
     BEST
    0.07
    Act Density 0.203%

    No Known Activations