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

    Neuronpedia

    INDEX
    Explanations

    summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ki
    -0.07
     supers
    -0.07
     Che
    -0.07
    قيام
    -0.06
    arti
    -0.06
    意外
    -0.06
    met
    -0.06
     Wan
    -0.06
    swagen
    -0.06
     Self
    -0.06
    POSITIVE LOGITS
     yaşad
    0.08
    OLUTION
    0.08
    质量问题
    0.07
     Hosp
    0.07
    产业集聚
    0.07
    뮌
    0.07
    偏低
    0.07
     quindi
    0.07
    production
    0.07
    恢复正常
    0.07
    Act Density 0.002%

    No Known Activations