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

    Neuronpedia

    INDEX
    Explanations

    Polit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ром
    -0.07
     号
    -0.07
    ellar
    -0.07
    umo
    -0.07
    су
    -0.06
    combe
    -0.06
    луг
    -0.06
    Mich
    -0.06
     arguments
    -0.06
    Modal
    -0.06
    POSITIVE LOGITS
    etration
    0.06
    인가
    0.06
    imizi
    0.06
    ~/
    0.06
     kalp
    0.06
     ره
    0.06
     زي
    0.06
    女子
    0.06
     hypers
    0.06
     Taş
    0.06
    Act Density 0.016%

    No Known Activations