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

    Neuronpedia

    INDEX
    Explanations

    Barrett/rett

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    삐
    -0.07
    setter
    -0.07
    更重要
    -0.07
    Ệ
    -0.07
     OrderedDict
    -0.07
    Ồ
    -0.07
    库
    -0.07
     Pills
    -0.07
     TIM
    -0.07
    有钱
    -0.07
    POSITIVE LOGITS
    닳
    0.06
    今后
    0.06
    |--
    0.06
    訓
    0.06
    Jun
    0.06
    /mark
    0.06
    trys
    0.06
    	trans
    0.06
    -register
    0.06
     squares
    0.06
    Act Density 0.013%

    No Known Activations