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

    Neuronpedia

    INDEX
    Explanations

    rattling sounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =='
    -0.08
    ]='\
    -0.08
    (QtCore
    -0.07
    =
    -0.07
    nev
    -0.07
    (Convert
    -0.07
     foram
    -0.07
    Clearly
    -0.07
    ='.$
    -0.07
    携手
    -0.07
    POSITIVE LOGITS
    午餐
    0.07
    的价格
    0.07
    فات
    0.07
     يتم
    0.07
    人民群众
    0.07
     Mitgli
    0.06
    ขนา
    0.06
    直观
    0.06
    𝇗
    0.06
     Reality
    0.06
    Act Density 0.003%

    No Known Activations