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

    Neuronpedia

    INDEX
    Explanations

    detect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ez
    -0.07
    .When
    -0.06
    nh
    -0.06
    Eigen
    -0.06
     ostr
    -0.06
     Kush
    -0.06
    abh
    -0.06
     ward
    -0.06
     Пет
    -0.06
    .modal
    -0.06
    POSITIVE LOGITS
    =o
    0.06
    _restrict
    0.06
    _quality
    0.06
    .Features
    0.06
    .viewModel
    0.06
    navigation
    0.06
     regarding
    0.06
     Minimum
    0.06
     ویژ
    0.06
     PropertyInfo
    0.06
    Act Density 0.021%

    No Known Activations