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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .Details
    -0.08
    쁭
    -0.07
    明白了
    -0.07
    절
    -0.07
    مطل
    -0.07
    hz
    -0.07
     Instrument
    -0.07
    转入
    -0.07
    -inverse
    -0.07
     Administrator
    -0.06
    POSITIVE LOGITS
    ève
    0.07
    AINER
    0.07
    orgia
    0.07
     stones
    0.07
    隔着
    0.07
    .H
    0.07
    ♱
    0.07
    윗
    0.06
    X
    0.06
    关羽
    0.06
    Act Density 0.001%

    No Known Activations