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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gep
    -0.06
     {...
    -0.06
     Enumerator
    -0.06
     멀
    -0.06
     مسئ
    -0.06
    Netflix
    -0.06
     目
    -0.06
     تنها
    -0.06
    operator
    -0.06
    OLEAN
    -0.06
    POSITIVE LOGITS
     Doctors
    0.07
     Filed
    0.07
    angled
    0.06
    .mo
    0.06
    lying
    0.06
     electrode
    0.06
    atisfaction
    0.06
     사이트
    0.06
     divorced
    0.06
     articles
    0.06
    Act Density 0.024%

    No Known Activations