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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рок
    -0.07
    _rect
    -0.07
    (direction
    -0.06
    آم
    -0.06
    rub
    -0.06
    ('\\
    -0.06
     worms
    -0.06
    _(
    -0.06
    """
    -0.06
     yoluyla
    -0.06
    POSITIVE LOGITS
     önemli
    0.07
     mpl
    0.06
    “There
    0.06
     simplest
    0.06
    unned
    0.06
    すぎ
    0.06
    ching
    0.06
    .MaxValue
    0.06
     Retrieves
    0.06
    ifers
    0.06
    Act Density 0.026%

    No Known Activations