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

    Neuronpedia

    INDEX
    Explanations

    website content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Passenger
    -0.06
    伏
    -0.06
    house
    -0.06
     Кол
    -0.06
    decor
    -0.06
     veut
    -0.06
     written
    -0.06
     thresh
    -0.06
    мм
    -0.06
     Sick
    -0.06
    POSITIVE LOGITS
     preventing
    0.07
    ươ
    0.06
     rawData
    0.06
    _WP
    0.06
     DIFF
    0.06
     Hulk
    0.06
    .png
    0.06
    ąż
    0.06
    )?;↵
    0.06
     معروف
    0.06
    Act Density 0.000%

    No Known Activations