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

    Neuronpedia

    INDEX
    Explanations

    вы

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bergen
    -0.07
     station
    -0.07
    芝
    -0.07
    َان
    -0.07
    pression
    -0.07
    /string
    -0.07
    กลาง
    -0.06
     begins
    -0.06
     tower
    -0.06
    :.:.:.:.:
    -0.06
    POSITIVE LOGITS
     вы
    0.09
    Вы
    0.08
     Вы
    0.08
    매
    0.07
     Goldman
    0.07
     определя
    0.06
    .GetString
    0.06
    Y
    0.06
    imu
    0.06
    вы
    0.06
    Act Density 0.015%

    No Known Activations