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

    Neuronpedia

    INDEX
    Explanations

    change their

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pune
    0.50
    CacheV
    0.48
    Odds
    0.43
    ብስብ
    0.43
    ע
    0.43
    нном
    0.43
    功率
    0.42
    ‌ترین
    0.42
    離島
    0.42
    Neha
    0.41
    POSITIVE LOGITS
    ai
    0.43
    andes
    0.41
    which
    0.40
    考试
    0.40
    ها
    0.40
    ethers
    0.40
     ist
    0.40
     MODKEY
    0.40
     மற்றொரு
    0.40
     Kü
    0.39
    Act Density 0.001%

    No Known Activations