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
    られて
    -0.07
     الساد
    -0.07
     bás
    -0.07
     différentes
    -0.07
    Goals
    -0.07
    也就是说
    -0.07
     بدأت
    -0.07
    minecraft
    -0.06
    就这样
    -0.06
    Arg
    -0.06
    POSITIVE LOGITS
    	version
    0.08
    寡
    0.07
    ߓ
    0.07
    Ⰽ
    0.07
     hàng
    0.07
    ьер
    0.06
     senators
    0.06
    万亿
    0.06
    ԛ
    0.06
    /Header
    0.06
    Act Density 0.013%

    No Known Activations