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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TorpedoStore
    0.43
    ))$.
    0.43
    LAYOUT
    0.43
    ))$
    0.42
    浣
    0.41
    社長
    0.38
    游泳
    0.38
    ))[
    0.38
    配套
    0.38
    ویان
    0.38
    POSITIVE LOGITS
     bikes
    0.46
    bikes
    0.44
     Shop
    0.42
     bicycles
    0.41
     wheel
    0.41
     Bikes
    0.41
     scooters
    0.41
    Shop
    0.41
     Wheel
    0.40
     Copenhagen
    0.39
    Act Density 0.001%

    No Known Activations