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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rewards
    -0.07
     rav
    -0.06
     เต
    -0.06
     Gems
    -0.06
     Gifts
    -0.06
    ->_
    -0.06
     بيانات
    -0.06
     Teen
    -0.06
     піз
    -0.06
    줄
    -0.06
    POSITIVE LOGITS
    DY
    0.06
    анов
    0.06
    ﾏ
    0.06
     scn
    0.06
     Tourism
    0.06
     Optical
    0.06
    annot
    0.06
     assess
    0.06
    cxx
    0.06
    Hallo
    0.06
    Act Density 0.000%

    No Known Activations