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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    確
    -0.08
     dataList
    -0.07
     whatsoever
    -0.07
     thumbnail
    -0.07
    وج
    -0.07
    _usr
    -0.07
    øre
    -0.07
     luggage
    -0.07
    Generator
    -0.06
     jersey
    -0.06
    POSITIVE LOGITS
     дос
    0.06
     Jak
    0.06
     arbe
    0.06
     अल
    0.06
     opak
    0.06
    (stage
    0.06
     참여
    0.06
     THEM
    0.06
     जर
    0.06
    �
    0.05
    Act Density 0.006%

    No Known Activations