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

    Neuronpedia

    INDEX
    Explanations

    position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    σή
    -0.06
     resets
    -0.06
    utt
    -0.06
    ذر
    -0.06
    소
    -0.06
    HI
    -0.06
     decorator
    -0.06
    'R
    -0.06
    _Update
    -0.06
    kont
    -0.06
    POSITIVE LOGITS
     alex
    0.07
    ?;↵↵
    0.07
    '});↵
    0.07
     consulta
    0.07
     Abdul
    0.06
     제목
    0.06
    ?[
    0.06
     Bergen
    0.06
    лиз
    0.06
     americ
    0.06
    Act Density 0.012%

    No Known Activations