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

    Neuronpedia

    INDEX
    Explanations

    Ancient recordkeeping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chicken
    -0.08
     GOP
    -0.08
     breastfeeding
    -0.08
     Chicken
    -0.08
     breathed
    -0.08
     Indie
    -0.08
    Spotify
    -0.08
     Breed
    -0.08
     PUBG
    -0.08
     hospice
    -0.08
    POSITIVE LOGITS
    账
    0.10
    記
    0.09
     accountants
    0.09
    算盘
    0.09
     bookkeeping
    0.09
    记录
    0.09
     नाग
    0.08
    报码
    0.08
     учета
    0.08
     письмен
    0.08
    Act Density 0.008%

    No Known Activations