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

    Neuronpedia

    INDEX
    Explanations

    official

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gateway
    -0.08
    DAO
    -0.07
    .AUTO
    -0.07
    تطوير
    -0.07
    提高
    -0.07
    ボー
    -0.07
    (Long
    -0.07
    ليم
    -0.07
    思
    -0.07
     steps
    -0.07
    POSITIVE LOGITS
     official
    0.08
     glUniform
    0.08
    同仁
    0.07
     сообщил
    0.07
    巫
    0.07
    تصريحات
    0.07
    slides
    0.07
    ไฟ
    0.07
     GU
    0.07
    zap
    0.07
    Act Density 0.009%

    No Known Activations