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

    Neuronpedia

    INDEX
    Explanations

    Article/URL references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Query
    -0.09
    🧑
    -0.07
    	options
    -0.07
    保荐
    -0.07
    xea
    -0.07
    익
    -0.07
    母校
    -0.07
    嫌疑
    -0.07
    石家
    -0.07
    鳇
    -0.07
    POSITIVE LOGITS
    쇠
    0.07
    ();"
    0.06
    odeled
    0.06
    ি�
    0.06
    ﳝ
    0.06
    ético
    0.06
    㳬
    0.06
    工作人员
    0.06
     tossed
    0.06
    Ɓ
    0.06
    Act Density 0.001%

    No Known Activations