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

    Neuronpedia

    INDEX
    Explanations

    Lists and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nh
    -0.08
     Residential
    -0.08
     Royale
    -0.08
     Concern
    -0.08
     اعلام
    -0.08
     manuals
    -0.07
     arenas
    -0.07
     exploitation
    -0.07
    	java
    -0.07
    Nh
    -0.07
    POSITIVE LOGITS
     nutrients
    0.12
     antioxidants
    0.11
     carbs
    0.11
     vitamin
    0.11
     vitamins
    0.11
    Calories
    0.11
     calories
    0.11
     calorie
    0.11
    protein
    0.10
     nutritious
    0.10
    Act Density 0.022%

    No Known Activations