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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]}$.
    0.49
    产能
    0.47
    hardhat
    0.45
    战斗
    0.44
    寻求
    0.44
    喜爱
    0.43
    ським
    0.43
    贯彻
    0.42
    权力
    0.42
    ۇل
    0.42
    POSITIVE LOGITS
     )(
    0.52
     )
    0.52
    int
    0.51
    -(
    0.50
     -(
    0.49
    orc
    0.49
    (((
    0.48
    !!)
    0.47
    ì
    0.47
    )=(
    0.47
    Act Density 0.018%

    No Known Activations