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

    Neuronpedia

    INDEX
    Explanations

    performing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msen
    0.66
    িসে
    0.64
    scraper
    0.62
     උ
    0.62
    itelisted
    0.61
    शंकर
    0.61
    সমান
    0.60
     cameos
    0.60
    ียว
    0.60
    လာ
    0.59
    POSITIVE LOGITS
     performed
    4.46
     conducted
    3.76
    performed
    3.75
     انجام
    3.54
    Performed
    3.50
     performing
    3.48
    Performing
    3.32
     perform
    3.28
     dilakukan
    3.25
    Perform
    3.23
    Act Density 1.162%

    No Known Activations