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

    Neuronpedia

    INDEX
    Explanations

    gas costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Main
    0.64
    Test
    0.60
    MAIN
    0.54
    main
    0.53
     test
    0.52
    test
    0.52
     main
    0.51
     MAIN
    0.50
     Main
    0.50
     Test
    0.49
    POSITIVE LOGITS
     Lore
    0.43
     WI
    0.40
    શા
    0.39
     Non
    0.38
     Paulo
    0.38
     गट
    0.38
    }}^{
    0.38
     Pug
    0.38
     lewis
    0.37
     неда
    0.37
    Act Density 0.002%

    No Known Activations