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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пла
    -0.06
    图片
    -0.06
    <quote
    -0.06
    -fixed
    -0.06
    	sp
    -0.06
    Dimensions
    -0.06
    Become
    -0.06
     브
    -0.06
    —↵↵
    -0.06
    parated
    -0.06
    POSITIVE LOGITS
    트
    0.07
    ANCED
    0.07
     pohled
    0.06
    assist
    0.06
    di
    0.06
    -x
    0.06
    _DEBUG
    0.06
    797
    0.06
    sg
    0.06
    ammers
    0.06
    Act Density 0.002%

    No Known Activations