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

    Neuronpedia

    INDEX
    Explanations

    references to meals and dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    meal times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.66
     SafeMath
    -0.60
    urlpatterns
    -0.60
     שוליים
    -0.57
     auroit
    -0.56
     desmotivaciones
    -0.52
     imprimée
    -0.51
     Económica
    -0.51
    útil
    -0.51
     AssemblyCulture
    -0.51
    POSITIVE LOGITS
     lunch
    1.13
     Lunch
    1.09
    Lunch
    1.09
     dinner
    1.06
    Dinner
    1.02
     Dinner
    1.02
    lunch
    0.94
     luncheon
    0.94
     breakfast
    0.92
     Breakfast
    0.92
    Act Density 0.016%

    No Known Activations