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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
     bak
    -0.07
    Khi
    -0.07
    PIP
    -0.07
    院
    -0.06
    _services
    -0.06
    ，这
    -0.06
    _Meta
    -0.06
     arreglo
    -0.06
    َي
    -0.06
    POSITIVE LOGITS
    (--
    0.06
    타이
    0.06
     appearing
    0.06
     Ảnh
    0.06
     октября
    0.06
    ยนตร
    0.06
     textu
    0.06
    metal
    0.06
    consulta
    0.06
     مدت
    0.06
    Act Density 0.005%

    No Known Activations