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

    Neuronpedia

    INDEX
    Explanations

    checking and verifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consistently
    0.90
     imagin
    0.82
     imaginative
    0.81
     systematic
    0.79
    create
    0.79
    Create
    0.75
     stepwise
    0.72
     persevere
    0.72
     점점
    0.72
     systematically
    0.72
    POSITIVE LOGITS
     reviewing
    1.36
     verification
    1.36
     check
    1.35
     review
    1.34
     verifying
    1.34
     verify
    1.33
     checking
    1.30
    確認
    1.30
     확인
    1.29
    verify
    1.28
    Act Density 0.624%

    No Known Activations