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

    Neuronpedia

    INDEX
    Explanations

    over/under representation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bris
    -0.07
     Ded
    -0.07
     motel
    -0.06
     TOP
    -0.06
    yon
    -0.06
    Pes
    -0.06
     přist
    -0.06
    onald
    -0.06
     kits
    -0.06
    rect
    -0.06
    POSITIVE LOGITS
    .paused
    0.07
    lags
    0.06
    ################
    0.06
    あの
    0.06
     Св
    0.06
    ораль
    0.06
    !!}
    0.06
    (class
    0.06
     ]]
    0.06
    ben
    0.06
    Act Density 0.218%

    No Known Activations