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

    Neuronpedia

    INDEX
    Explanations

    references to recipes and cooking resources

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

    healthy dinner recipe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynnwys
    -0.52
    AsUp
    -0.50
    дивиду
    -0.50
     Sext
    -0.49
     Descartes
    -0.49
    spection
    -0.49
    éfonos
    -0.48
    Javadoc
    -0.48
     dieną
    -0.47
     helado
    -0.47
    POSITIVE LOGITS
     recipe
    1.02
     recipes
    0.98
     RECIPES
    0.82
     Recipes
    0.81
    recipes
    0.80
    Recipes
    0.78
     Recipe
    0.77
     RECIPE
    0.77
    recipe
    0.76
     resep
    0.71
    Act Density 0.038%

    No Known Activations