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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ду
    -0.07
    endereco
    -0.07
    填报
    -0.07
    wä
    -0.07
     Xen
    -0.07
     corrupt
    -0.07
     Fresno
    -0.06
    驽
    -0.06
    约谈
    -0.06
    	where
    -0.06
    POSITIVE LOGITS
     ____
    0.07
    .AP
    0.07
     전체
    0.07
    宜昌
    0.07
    .byId
    0.07
    某某
    0.06
    Orange
    0.06
    變化
    0.06
     depended
    0.06
     sculptures
    0.06
    Act Density 0.001%

    No Known Activations