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

    Neuronpedia

    INDEX
    Explanations

    develop and create actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Has
    0.75
    包含了
    0.73
    has
    0.70
    Don
    0.67
     wären
    0.67
    expectation
    0.65
    สิ่งที่
    0.64
    requires
    0.64
    Мы
    0.64
    際は
    0.63
    POSITIVE LOGITS
     develop
    1.60
     achieve
    1.50
     take
    1.50
     establish
    1.48
     identify
    1.47
     understand
    1.45
     navigate
    1.44
     generate
    1.43
     communicate
    1.42
     create
    1.42
    Act Density 0.082%

    No Known Activations