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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Precision
    -0.06
    振
    -0.06
    .findElement
    -0.06
    ציע
    -0.06
    为了让
    -0.06
     hứng
    -0.06
    借此
    -0.06
    텐
    -0.06
    eted
    -0.06
    뉨
    -0.06
    POSITIVE LOGITS
    (storage
    0.08
     Breaking
    0.07
     ―
    0.07
    ({});↵
    0.07
     Jak
    0.07
     série
    0.07
    _low
    0.07
     headings
    0.07
    .notifications
    0.07
     runway
    0.07
    Act Density 0.001%

    No Known Activations