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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    所
    -0.08
     jap
    -0.08
    (
    -0.07
    續
    -0.07
     tend
    -0.07
     being
    -0.07
    jual
    -0.07
     het
    -0.07
    嗑
    -0.07
    （
    -0.07
    POSITIVE LOGITS
    Carlos
    0.08
     régl
    0.07
     Writes
    0.07
    PS
    0.07
     Dũng
    0.07
    腿部
    0.07
    �
    0.07
    📏
    0.07
    postalcode
    0.07
    иков
    0.07
    Act Density 0.007%

    No Known Activations