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

    Neuronpedia

    INDEX
    Explanations

    navigating to settings and menus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     optimized
    0.39
    yles
    0.38
     vortices
    0.37
     economically
    0.36
    ہوری
    0.36
     speculated
    0.36
    featuring
    0.36
     tailored
    0.36
     sauv
    0.35
     pediatric
    0.35
    POSITIVE LOGITS
     Settings
    0.94
     меню
    0.94
    Settings
    0.86
     dashboard
    0.85
     settings
    0.83
     menu
    0.82
     console
    0.80
     Dashboard
    0.80
     Einstellungen
    0.79
     GUI
    0.78
    Act Density 0.063%

    No Known Activations