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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    叹了口气
    -0.07
    嵅
    -0.07
    -badge
    -0.07
     where
    -0.07
     sple
    -0.07
    _COMMENT
    -0.07
    极度
    -0.07
     whereby
    -0.07
     Senior
    -0.07
    にとって
    -0.07
    POSITIVE LOGITS
     determin
    0.07
    ざ
    0.07
     benefited
    0.07
     accounted
    0.07
     Accounting
    0.07
    ParameterValue
    0.06
    ::::::
    0.06
    stell
    0.06
    ⇝
    0.06
    保留
    0.06
    Act Density 0.008%

    No Known Activations