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

    Neuronpedia

    INDEX
    Explanations

    breakfast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tonight
    1.25
     Tonight
    1.02
    Tonight
    0.96
     humaines
    0.81
     cucina
    0.80
     begyn
    0.80
    uz
    0.80
    ï
    0.80
     muziek
    0.79
    ën
    0.77
    POSITIVE LOGITS
     Breakfast
    1.38
     breakfast
    1.24
    Breakfast
    1.16
     Morning
    1.13
    朝
    1.09
     morning
    1.08
     मॉर्निंग
    1.08
     breakfasts
    1.08
     утром
    1.08
    morning
    1.05
    Act Density 0.075%

    No Known Activations