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

    Neuronpedia

    INDEX
    Explanations

    eating actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Carpet
    0.44
     carpet
    0.43
     Narcotics
    0.38
     Colleen
    0.37
     Héctor
    0.37
    ্রান্ত
    0.37
    Furn
    0.37
     mutating
    0.37
     вывести
    0.36
    书城
    0.36
    POSITIVE LOGITS
     eating
    1.29
     Eating
    1.20
    Eating
    1.18
    eating
    1.13
     eat
    1.09
     chewing
    1.06
    咀
    1.04
    食べ
    1.03
     Eat
    1.02
     chew
    1.02
    Act Density 0.032%

    No Known Activations