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

    Neuronpedia

    INDEX
    Explanations

    Code diffs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adders
    -0.08
    ideshow
    -0.07
     BYTE
    -0.07
     Rohing
    -0.06
     butto
    -0.06
     drone
    -0.06
    íky
    -0.06
    .GetAxis
    -0.06
     StartTime
    -0.06
    PagerAdapter
    -0.06
    POSITIVE LOGITS
     أص
    0.07
     reference
    0.07
     التع
    0.07
     intercourse
    0.06
    (MPI
    0.06
    single
    0.06
     anticipated
    0.06
    нов
    0.06
     Μπ
    0.06
    ालक
    0.06
    Act Density 0.002%

    No Known Activations