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

    Neuronpedia

    INDEX
    Explanations

    calories and heat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     democracia
    0.50
     Democr
    0.42
     limitaciones
    0.41
     Justiça
    0.40
    シャレ
    0.39
    𝒔
    0.39
     dispositif
    0.38
     ServicePolicy
    0.38
     ForeignKey
    0.38
     Stellung
    0.38
    POSITIVE LOGITS
     calories
    0.90
     calorie
    0.88
     Calories
    0.80
    calories
    0.75
     caloric
    0.74
    Calories
    0.73
     kalor
    0.71
     कैलो
    0.70
    calorie
    0.68
     calorías
    0.66
    Act Density 0.075%

    No Known Activations