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

    Neuronpedia

    INDEX
    Explanations

    width or height

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     우리나
    -0.08
     Remark
    -0.07
    	TArray
    -0.07
    됏
    -0.07
    项链
    -0.07
    ﴼ
    -0.07
     stared
    -0.06
     reve
    -0.06
    年来
    -0.06
     masc
    -0.06
    POSITIVE LOGITS
     cử
    0.07
    泂
    0.07
     theater
    0.07
    得起
    0.07
    切尔
    0.07
    改变了
    0.07
     يستطيع
    0.07
    .order
    0.07
     cập
    0.07
    حوال
    0.07
    Act Density 0.001%

    No Known Activations