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

    Neuronpedia

    INDEX
    Explanations

    Math/physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ાની
    -0.08
    API
    -0.08
    ાનો
    -0.08
    Api
    -0.08
     ઇ
    -0.07
    ));↵
    -0.07
    ાનું
    -0.07
    -api
    -0.07
    向
    -0.07
    .quick
    -0.07
    POSITIVE LOGITS
     Scaling
    0.11
     scaling
    0.11
    Scaling
    0.10
     상승
    0.10
     steig
    0.09
    _scal
    0.09
     сравнению
    0.09
     Twice
    0.09
     Comparable
    0.09
     Comparative
    0.09
    Act Density 0.045%

    No Known Activations