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

    Neuronpedia

    INDEX
    Explanations

    numbers and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.36
     an
    0.32
     сом
    0.31
    TestMethod
    0.30
    LAG
    0.30
     தொற்று
    0.29
     위해
    0.29
    ີ
    0.29
    篙
    0.29
    menuCategory
    0.28
    POSITIVE LOGITS
     people
    0.44
    th
    0.40
     మంది
    0.40
     avatars
    0.39
     लोग
    0.39
    soldiers
    0.38
     individuals
    0.37
    ম্পতি
    0.37
     bowlers
    0.36
     peuple
    0.36
    Act Density 0.084%

    No Known Activations