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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lincoln
    -0.06
    控制
    -0.06
     execution
    -0.06
     Haus
    -0.06
    (nil
    -0.06
     Resource
    -0.06
    nak
    -0.06
    country
    -0.06
     Gins
    -0.06
     Supervisor
    -0.06
    POSITIVE LOGITS
    (IService
    0.07
     reloadData
    0.07
    pdf
    0.06
     ‏
    0.06
    tarı
    0.06
     دولار
    0.06
    0.06
     __________________________________
    0.06
    باش
    0.06
     шт
    0.06
    Act Density 0.056%

    No Known Activations