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

    Neuronpedia

    INDEX
    Explanations

    math notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     müş
    -0.08
    unte
    -0.08
     seminar
    -0.08
    sera
    -0.08
     Weather
    -0.07
     WEATHER
    -0.07
     Tutors
    -0.07
     javax
    -0.07
     tuto
    -0.07
    Weather
    -0.07
    POSITIVE LOGITS
     ವರ್ಷ
    0.09
    五
    0.09
     potência
    0.08
     ವರ್ಷದ
    0.08
     cruel
    0.08
    今晚
    0.08
     puissance
    0.08
    ARR
    0.08
    順位
    0.07
    íl
    0.07
    Act Density 0.024%

    No Known Activations