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

    Neuronpedia

    INDEX
    Explanations

    variations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sphere
    -0.07
    _set
    -0.07
     مسیر
    -0.07
    cone
    -0.07
    int
    -0.07
     palabra
    -0.07
    Someone
    -0.07
    Square
    -0.06
     речов
    -0.06
    Ol
    -0.06
    POSITIVE LOGITS
     variations
    0.10
     variation
    0.08
    ���
    0.06
     iterations
    0.06
     Лит
    0.06
     вариант
    0.06
    _heads
    0.06
    $http
    0.06
     　 　 　 　
    0.06
    _comm
    0.06
    Act Density 0.020%

    No Known Activations