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

    Neuronpedia

    INDEX
    Explanations

    ", '"', "quietly", "data"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িয়াছিলেন
    0.41
    Vaterpolo
    0.41
    টিয়
    0.41
    textFont
    0.40
    <unused743>
    0.40
    нын
    0.40
    ћин
    0.39
    謢
    0.39
    કારે
    0.39
    iffent
    0.38
    POSITIVE LOGITS
     chance
    0.39
     Tomorrow
    0.38
     Chance
    0.38
    癥
    0.37
    หรือไม่
    0.36
     Mengen
    0.35
     upward
    0.35
     Gaia
    0.35
     Alice
    0.34
     Edited
    0.34
    Act Density 0.000%

    No Known Activations