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

    Neuronpedia

    INDEX
    Explanations

    manual page documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DataTask
    -0.07
    .xlsx
    -0.07
     gaat
    -0.07
     gy
    -0.06
     sust
    -0.06
     dataList
    -0.06
     negot
    -0.06
    ፣
    -0.06
    .When
    -0.06
    ዝ
    -0.06
    POSITIVE LOGITS
    roducing
    0.09
    ирование
    0.08
    rai
    0.07
     Witness
    0.07
    ne
    0.07
    爸妈
    0.07
    AINS
    0.06
    	Null
    0.06
     إي
    0.06
    在整个
    0.06
    Act Density 0.020%

    No Known Activations