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

    Neuronpedia

    INDEX
    Explanations

    numbers and their labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onRouteChange
    0.33
    fireFlower
    0.31
    getStudentNo
    0.30
    踺
    0.30
    BlockUsed
    0.30
    getBlueTeam
    0.29
     ব্যাকটেরিয়া
    0.29
    NumConst
    0.29
    䟧
    0.29
    薊
    0.28
    POSITIVE LOGITS
    2
    0.52
    4
    0.43
    3
    0.42
    5
    0.42
     для
    0.35
    D
    0.35
    d
    0.35
    6
    0.35
    H
    0.34
     two
    0.34
    Act Density 0.106%

    No Known Activations