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

    Neuronpedia

    INDEX
    Explanations

    renovations and alterations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mma
    -0.06
    雖然
    -0.06
     Scientist
    -0.06
    锜
    -0.06
    이나
    -0.06
    isten
    -0.06
    [ip
    -0.06
    .NoSuch
    -0.06
     organizing
    -0.06
    -life
    -0.06
    POSITIVE LOGITS
     Алекс
    0.08
    كسر
    0.08
    馈
    0.07
    ⚚
    0.07
     aliment
    0.07
    bread
    0.07
    햅
    0.07
    문화
    0.07
    戏剧
    0.07
    泪
    0.07
    Act Density 0.050%

    No Known Activations