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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _MOUSE
    -0.07
    Other
    -0.07
    鹉
    -0.07
    _DOT
    -0.06
    一句话
    -0.06
     Easter
    -0.06
    公社
    -0.06
    流产
    -0.06
     tolerant
    -0.06
    老子
    -0.06
    POSITIVE LOGITS
     sublime
    0.07
    ano
    0.07
    化学品
    0.07
     trọng
    0.07
    !".
    0.07
    的历史
    0.07
    뇨
    0.07
    🙏
    0.07
    argas
    0.07
     Tempo
    0.07
    Act Density 0.000%

    No Known Activations