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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     minors
    -0.07
     altın
    -0.07
    -it
    -0.07
     tro
    -0.07
    交替
    -0.07
     Cot
    -0.07
    Pot
    -0.07
     mol
    -0.07
    鄉
    -0.06
     tranquil
    -0.06
    POSITIVE LOGITS
    /(?
    0.07
    通行
    0.07
    خالف
    0.07
    察
    0.07
    AWS
    0.07
     judged
    0.06
    舞
    0.06
    แนวทาง
    0.06
    EndInit
    0.06
    𠅤
    0.06
    Act Density 0.055%

    No Known Activations