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

    Neuronpedia

    INDEX
    Explanations

    math competitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restoration
    -0.09
     drywall
    -0.09
     wrinkle
    -0.09
     healed
    -0.08
     impaired
    -0.08
     sludge
    -0.08
     Dryer
    -0.08
     wrinkles
    -0.08
     estrogen
    -0.08
     безопас
    -0.08
    POSITIVE LOGITS
     olymp
    0.12
     олим
    0.12
     प्रतियोग
    0.12
     Olymp
    0.11
     contest
    0.10
     Invitational
    0.10
     competitions
    0.10
    一等奖
    0.10
    Junior
    0.10
     polynomial
    0.10
    Act Density 0.015%

    No Known Activations