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

    Neuronpedia

    INDEX
    Explanations

    Book/article/course titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     _(
    -0.09
     тура
    -0.08
    atorial
    -0.08
    жащ
    -0.08
     Gut
    -0.08
    <IS
    -0.07
    Gut
    -0.07
    녁
    -0.07
    �
    -0.07
    คำ
    -0.07
    POSITIVE LOGITS
    ��������
    0.08
    》（
    0.08
    ...',
    0.08
    ...'
    0.07
    ...",
    0.07
    ার
    0.07
     ..."
    0.07
    ..."
    0.07
     hens
    0.07
    ���
    0.07
    Act Density 0.021%

    No Known Activations