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

    Neuronpedia

    INDEX
    Explanations

    calories and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    妽
    0.45
    คัญ
    0.42
    лось
    0.40
    眹
    0.40
    وح
    0.39
    等的
    0.39
     Datei
    0.38
    richtung
    0.38
     beteiligt
    0.38
     kompos
    0.38
    POSITIVE LOGITS
     Calories
    0.55
     calorie
    0.46
     calories
    0.45
    Calories
    0.43
     буквально
    0.41
     Household
    0.40
     Q
    0.40
    olding
    0.40
     Meal
    0.40
     Caldwell
    0.39
    Act Density 0.001%

    No Known Activations