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

    Neuronpedia

    INDEX
    Explanations

    <=

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jour
    -0.08
    ሩ
    -0.08
    实践中
    -0.07
    现代社会
    -0.07
    áz
    -0.07
     gentleman
    -0.07
    ✙
    -0.07
    sheets
    -0.07
    ربط
    -0.07
    InvalidArgumentException
    -0.07
    POSITIVE LOGITS
     Bryan
    0.09
    哆
    0.07
    膽
    0.07
     deform
    0.07
    뺑
    0.07
     Marvel
    0.07
    比亚迪
    0.07
    쪄
    0.07
    銀
    0.06
     мя
    0.06
    Act Density 0.023%

    No Known Activations