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

    Neuronpedia

    INDEX
    Explanations

    had

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     budgets
    -0.08
     Cape
    -0.07
    资
    -0.07
     ecology
    -0.06
    ologi
    -0.06
    IQUE
    -0.06
    /message
    -0.06
     gray
    -0.06
     Notes
    -0.06
     Academic
    -0.06
    POSITIVE LOGITS
     soda
    0.07
     toàn
    0.06
    Rock
    0.06
    getParent
    0.06
    ंब
    0.06
     ради
    0.06
    �
    0.06
     Nicar
    0.06
    şı
    0.06
     vap
    0.06
    Act Density 0.029%

    No Known Activations