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

    Neuronpedia

    INDEX
    Explanations

    standard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cathy
    -0.07
    Shadow
    -0.07
    ying
    -0.07
     Reflex
    -0.06
    ERCHANT
    -0.06
     gps
    -0.06
    ère
    -0.06
    енко
    -0.06
    ér
    -0.06
    _clock
    -0.06
    POSITIVE LOGITS
     standard
    0.07
    نتاج
    0.06
     медицин
    0.06
    CM
    0.06
    Except
    0.06
    0.06
    चन
    0.06
     ortalama
    0.06
     ><?
    0.06
     Cass
    0.06
    Act Density 0.015%

    No Known Activations