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

    Neuronpedia

    INDEX
    Explanations

    capital

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Prov
    -0.08
     kommet
    -0.08
     competit
    -0.08
     Cooper
    -0.08
     šal
    -0.08
    Dealer
    -0.07
    Leon
    -0.07
    Italian
    -0.07
    bron
    -0.07
     sheriff
    -0.07
    POSITIVE LOGITS
     expenditure
    0.10
     expenditures
    0.10
     ಯೋಜ
    0.09
     plans
    0.09
     പദ്ധ
    0.09
     പദ്ധത
    0.09
     excessive
    0.09
     योजन
    0.08
     excursions
    0.08
     surprises
    0.08
    Act Density 0.005%

    No Known Activations