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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _POLL
    -0.07
    菹
    -0.07
    黄瓜
    -0.06
    OOSE
    -0.06
    得出
    -0.06
     tapi
    -0.06
     потом
    -0.06
     pund
    -0.06
     pca
    -0.06
     Mundo
    -0.06
    POSITIVE LOGITS
     superior
    0.07
     lighter
    0.07
     Sony
    0.07
    ittance
    0.07
    Todd
    0.06
    三季度
    0.06
    九
    0.06
     chair
    0.06
    _sales
    0.06
     Sinclair
    0.06
    Act Density 0.045%

    No Known Activations