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

    Neuronpedia

    INDEX
    Explanations

    polym

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -circle
    -0.07
     Courage
    -0.07
    能源
    -0.06
    653
    -0.06
     противоп
    -0.06
     mj
    -0.06
    [msg
    -0.06
    妙
    -0.06
     attendance
    -0.06
     физ
    -0.06
    POSITIVE LOGITS
     tweak
    0.07
    .Features
    0.06
    imu
    0.06
    wechat
    0.06
    یزی
    0.06
    ывая
    0.06
    .Local
    0.06
    olate
    0.06
     Thánh
    0.06
    params
    0.06
    Act Density 0.006%

    No Known Activations