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

    Neuronpedia

    INDEX
    Explanations

    Studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <form
    -0.07
     //@
    -0.07
    prix
    -0.07
    ><?
    -0.07
    ı
    -0.07
    frog
    -0.07
    (BuildContext
    -0.06
     сп
    -0.06
    //@
    -0.06
     Lords
    -0.06
    POSITIVE LOGITS
    ++++++++
    0.07
     Barang
    0.06
     출
    0.06
     Thánh
    0.06
     trước
    0.06
     Taipei
    0.06
    loe
    0.06
     ジ
    0.06
     disp
    0.06
     rồi
    0.06
    Act Density 0.049%

    No Known Activations