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

    Neuronpedia

    INDEX
    Explanations

    reports and ratings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ubu
    -0.06
     の
    -0.06
     Tradable
    -0.06
    ukes
    -0.06
    ,opt
    -0.06
    #print
    -0.06
     props
    -0.06
    licate
    -0.06
    .After
    -0.06
    ....↵
    -0.06
    POSITIVE LOGITS
    lük
    0.07
     latter
    0.07
     gerek
    0.06
     instituted
    0.06
     sensible
    0.06
    .makedirs
    0.06
     Дон
    0.06
    ении
    0.06
     dwind
    0.06
    _equalTo
    0.06
    Act Density 0.016%

    No Known Activations