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

    Neuronpedia

    INDEX
    Explanations

    sports games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，这
    -0.07
    ��
    -0.06
    縮
    -0.06
    이라는
    -0.06
    쓰
    -0.06
     trúc
    -0.06
    ugu
    -0.06
     επ
    -0.06
     trị
    -0.06
    swap
    -0.05
    POSITIVE LOGITS
    !");↵
    0.07
    حت
    0.07
    onder
    0.06
    }-${
    0.06
    (EFFECT
    0.06
    /problems
    0.06
    ictor
    0.06
    ısından
    0.06
     HF
    0.06
    (startDate
    0.06
    Act Density 0.005%

    No Known Activations