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

    Neuronpedia

    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CTRL
    -0.07
    网站
    -0.06
    -su
    -0.06
     брон
    -0.06
    	sm
    -0.06
    ược
    -0.06
     вку
    -0.06
    _RGB
    -0.06
    無し�
    -0.06
    iệu
    -0.06
    POSITIVE LOGITS
     disruption
    0.06
     criticized
    0.06
     Guinea
    0.06
    оном
    0.06
    apur
    0.06
     Pharmacy
    0.06
     Renaissance
    0.06
    borg
    0.06
     attachment
    0.06
    (moment
    0.06
    Act Density 0.002%

    No Known Activations