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

    Neuronpedia

    INDEX
    Explanations

    to for ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     everything
    0.70
     Leveraging
    0.70
     Everything
    0.70
     Incoming
    0.65
    ischer
    0.62
     mọi
    0.62
     eigentlich
    0.62
    かもしれません
    0.61
     Fast
    0.61
     từng
    0.60
    POSITIVE LOGITS
    到
    1.64
     إلى
    1.48
     الى
    1.41
     hingga
    1.33
    年至
    1.29
     đến
    1.23
     到
    1.21
     تا
    1.15
     έως
    1.12
    日至
    1.09
    Act Density 0.276%

    No Known Activations