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

    Neuronpedia

    INDEX
    Explanations

    enumerate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $a
    -0.09
     위치
    -0.07
    selection
    -0.07
     gasoline
    -0.07
    це
    -0.07
    леч
    -0.06
     Dinner
    -0.06
    022
    -0.06
     развитие
    -0.06
     DB
    -0.06
    POSITIVE LOGITS
    рит
    0.06
    unteer
    0.06
    spam
    0.06
    ね
    0.06
    สาย
    0.06
    ウン
    0.06
    .enum
    0.06
     مت
    0.06
     bahsed
    0.06
     قص
    0.06
    Act Density 0.002%

    No Known Activations