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

    Neuronpedia

    INDEX
    Explanations

    model code block start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     optimised
    0.47
     optimal
    0.42
    0.42
     ham
    0.41
     optimized
    0.40
     optimum
    0.40
     Values
    0.40
     exercised
    0.40
     playerData
    0.40
    ierzchn
    0.38
    POSITIVE LOGITS
    main
    0.40
    usiness
    0.39
    सबसे
    0.38
     состо
    0.38
    路
    0.38
    Business
    0.37
    Privacy
    0.37
    MAIN
    0.37
    下载
    0.37
    road
    0.36
    Act Density 0.011%

    No Known Activations