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

    Neuronpedia

    INDEX
    Explanations

    Rules and requirements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iếu
    -0.07
    ensored
    -0.07
    脂肪
    -0.07
    奖励
    -0.07
    coop
    -0.07
    Filters
    -0.07
     Johnston
    -0.07
    скоп
    -0.07
     contenu
    -0.07
    阻碍
    -0.06
    POSITIVE LOGITS
     самого
    0.08
    $path
    0.07
    /I
    0.06
    年初
    0.06
    ">'↵
    0.06
     forgiven
    0.06
    attering
    0.06
     진
    0.06
    上年
    0.06
     Martha
    0.06
    Act Density 0.034%

    No Known Activations