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

    Neuronpedia

    INDEX
    Explanations

    whole and processed foods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vegetarians
    0.54
     vegans
    0.49
     yogurt
    0.48
     Dietary
    0.48
     Vegetarian
    0.48
     diet
    0.47
     yoghurt
    0.47
     risotto
    0.47
     drink
    0.47
     Protein
    0.46
    POSITIVE LOGITS
    processed
    0.46
     inorganic
    0.46
     unnatural
    0.41
     submissions
    0.41
    simple
    0.40
     organically
    0.40
    TransactionLog
    0.40
     обработки
    0.40
    ख
    0.40
     artificial
    0.40
    Act Density 0.028%

    No Known Activations