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

    Neuronpedia

    INDEX
    Explanations

    Legal/Official documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    主持
    -0.07
     character
    -0.07
    	Map
    -0.07
     annum
    -0.06
    制定
    -0.06
    _DIG
    -0.06
     employed
    -0.06
    chair
    -0.06
    太太
    -0.06
     degrade
    -0.06
    POSITIVE LOGITS
    אבל
    0.08
    พล
    0.07
     researching
    0.07
    인이
    0.07
     Yii
    0.07
     Plex
    0.07
     factual
    0.07
    蓝色
    0.07
     BI
    0.07
     EE
    0.07
    Act Density 0.043%

    No Known Activations