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

    Neuronpedia

    INDEX
    Explanations

    news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spaceship
    -0.07
     fuel
    -0.07
     Makeup
    -0.07
     هنا
    -0.07
     亚洲
    -0.07
     Rune
    -0.07
     DA
    -0.06
     Mongo
    -0.06
    iero
    -0.06
    DAO
    -0.06
    POSITIVE LOGITS
    con
    0.06
    .DateFormat
    0.06
     ≈
    0.06
     addressing
    0.06
    (e
    0.06
    :green
    0.06
     trẻ
    0.06
    の上
    0.06
    _recent
    0.06
     needing
    0.06
    Act Density 0.024%

    No Known Activations