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

    Neuronpedia

    INDEX
    Explanations

    Measurement instruments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    旅游
    -0.07
     축구
    -0.07
     helper
    -0.06
    DESCRIPTION
    -0.06
    国家
    -0.06
     §
    -0.06
     occupancy
    -0.06
     islands
    -0.06
    よね
    -0.06
     ground
    -0.06
    POSITIVE LOGITS
    บล
    0.06
    ��
    0.06
    シャ
    0.06
     Saddam
    0.06
     бла
    0.06
    、ア
    0.06
     yiy
    0.06
     Increment
    0.06
    іття
    0.06
    бора
    0.06
    Act Density 0.039%

    No Known Activations