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

    Neuronpedia

    INDEX
    Explanations

    placeholder token

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    டுகளில்
    0.77
    lifer
    0.73
    Assemblée
    0.72
    丵
    0.72
    DialogOpen
    0.70
    रोला
    0.69
    rrrr
    0.69
    minimum
    0.69
    acionales
    0.69
    спери
    0.68
    POSITIVE LOGITS
     main
    1.19
     Main
    1.17
    Main
    1.01
    main
    1.00
    主
    0.97
     Haupt
    0.93
     主
    0.91
     الرئيسية
    0.90
    MAIN
    0.90
     główn
    0.90
    Act Density 0.009%

    No Known Activations