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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Give
    -0.08
    あって
    -0.07
     Ashe
    -0.07
    .bmp
    -0.07
    永不
    -0.07
    hire
    -0.07
    (console
    -0.07
     allowance
    -0.07
    accumulator
    -0.07
    虎卫
    -0.07
    POSITIVE LOGITS
     userId
    0.08
     нуж
    0.07
    	input
    0.07
     Rx
    0.07
     +#
    0.07
     максималь
    0.07
     mariage
    0.07
    休息
    0.07
    /id
    0.07
    等内容
    0.06
    Act Density 0.009%

    No Known Activations