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

    Neuronpedia

    INDEX
    Explanations

    FOR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _create
    -0.07
     martyr
    -0.07
     خواه
    -0.06
     Polynomial
    -0.06
    ｊ
    -0.06
    (long
    -0.06
    .piece
    -0.06
     magna
    -0.06
    (Entity
    -0.06
     beh
    -0.06
    POSITIVE LOGITS
    errar
    0.07
    tek
    0.06
    .Extensions
    0.06
    For
    0.06
    fad
    0.06
    688
    0.06
     For
    0.06
     inland
    0.06
     حالت
    0.06
     нанес
    0.06
    Act Density 0.001%

    No Known Activations