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

    Neuronpedia

    INDEX
    Explanations

    windows update component issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    飞
    0.48
     Jewel
    0.46
     অসুবিধা
    0.46
    おく
    0.46
    বেদ
    0.46
     企业
    0.46
     crebre
    0.46
     عمليه
    0.46
     INSEE
    0.45
     jewel
    0.45
    POSITIVE LOGITS
     наме
    0.45
    (
    0.45
    科学
    0.45
    isation
    0.44
    рон
    0.43
     rejuvenating
    0.42
    िय
    0.42
     telescope
    0.42
    ās
    0.41
     сигна
    0.41
    Act Density 0.001%

    No Known Activations