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

    Neuronpedia

    INDEX
    Explanations

    code expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	record
    -0.07
    advert
    -0.07
    šlo
    -0.07
     Jarvis
    -0.07
     приступ
    -0.07
    igrams
    -0.06
    .Private
    -0.06
    จำก
    -0.06
    criteria
    -0.06
    unpack
    -0.06
    POSITIVE LOGITS
     US
    0.07
     enemy
    0.06
    iesz
    0.06
    (Game
    0.06
     Debbie
    0.06
    ToDo
    0.06
    .flatMap
    0.06
     running
    0.06
    _five
    0.05
     ******************************************************************************/↵
    0.05
    Act Density 0.013%

    No Known Activations