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

    Neuronpedia

    INDEX
    Explanations

    main(args) or main(argc, argv)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exhaustive
    0.46
    运气
    0.45
    0.41
    indagi
    0.39
    甭
    0.39
    "]])
    0.39
    ઉન
    0.39
     dunno
    0.38
    បើ
    0.38
     దీని
    0.38
    POSITIVE LOGITS
     dengan
    0.40
     kami
    0.39
     mang
    0.38
     melalui
    0.38
    ceria
    0.37
     குறைவாக
    0.37
    }{{
    0.36
    hés
    0.36
     dalla
    0.36
    smaller
    0.36
    Act Density 0.001%

    No Known Activations