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

    Neuronpedia

    INDEX
    Explanations

    code snippets/technical communications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ">//
    -0.79
     المعيارى
    -0.67
    ждый
    -0.65
    :✨
    -0.61
    #+#
    -0.60
     hvilket
    -0.60
    leski
    -0.60
    OfMonth
    -0.59
    }());
    -0.59
    owohl
    -0.57
    POSITIVE LOGITS
    لق
    0.49
    a
    0.46
     Camin
    0.45
     dậy
    0.44
    an
    0.43
    able
    0.43
     hug
    0.43
    als
    0.41
    al
    0.41
    che
    0.41
    Act Density 0.057%

    No Known Activations