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

    Neuronpedia

    INDEX
    Explanations

    quick weeknight meals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subtle
    0.39
     Goliath
    0.39
     unters
    0.38
     grotes
    0.38
     interloc
    0.36
     raref
    0.36
     Landschaft
    0.36
     amended
    0.35
     sincerity
    0.35
     dialect
    0.35
    POSITIVE LOGITS
     cooking
    0.94
     recipes
    0.93
    Cooking
    0.90
     Cooking
    0.88
     Recipes
    0.88
    Recipes
    0.87
     cookbook
    0.85
    cooking
    0.85
     cookbooks
    0.85
     meals
    0.84
    Act Density 0.045%

    No Known Activations