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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dak
    -0.07
    幸
    -0.07
     Mug
    -0.07
     původ
    -0.06
     socially
    -0.06
    iyat
    -0.06
    린이
    -0.06
     Studi
    -0.06
     πολι
    -0.06
    σμού
    -0.06
    POSITIVE LOGITS
     perder
    0.06
    gly
    0.06
     січня
    0.06
     watchdog
    0.06
     TypeInfo
    0.06
    |^
    0.06
    laví
    0.06
     trem
    0.06
    efore
    0.06
     Alexandra
    0.06
    Act Density 0.021%

    No Known Activations