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

    Neuronpedia

    INDEX
    Explanations

    broccoli and kale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ρης
    0.46
    ्यर्थ
    0.39
    inafter
    0.39
    جهه
    0.39
    Corpor
    0.38
    paypal
    0.38
     varn
    0.37
    你说
    0.37
    បញ្ចប់
    0.37
     pem
    0.37
    POSITIVE LOGITS
     broccoli
    0.89
     kale
    0.88
     Broccoli
    0.80
     Kale
    0.79
    Kale
    0.78
    🥦
    0.70
     cabbage
    0.67
    broccoli
    0.67
     Kaleidoscope
    0.66
     cauliflower
    0.62
    Act Density 0.008%

    No Known Activations