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

    Neuronpedia

    INDEX
    Explanations

    above target

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endIndex
    0.44
    粌
    0.40
    prices
    0.39
    FRING
    0.39
    繁忙時間服務
    0.39
     ट्रेस
    0.38
    據
    0.38
     giá
    0.38
     passwd
    0.37
    имость
    0.37
    POSITIVE LOGITS
     gemidd
    0.42
     Target
    0.42
    平均
    0.42
     Average
    0.40
     long
    0.40
     average
    0.40
     평균
    0.40
     AVERAGE
    0.39
     Aver
    0.39
     Targets
    0.39
    Act Density 0.001%

    No Known Activations