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

    Neuronpedia

    INDEX
    Explanations

    physical or mathematical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사용자
    0.64
     benutzer
    0.62
     उपयोगकर्ता
    0.61
     consommateurs
    0.61
     orçamento
    0.61
     kullanıcı
    0.60
     reseller
    0.58
     Lazada
    0.57
     Benutzer
    0.57
     reconoce
    0.57
    POSITIVE LOGITS
     asymptotics
    0.64
     simulations
    0.59
     nuclear
    0.57
     physics
    0.57
    analysis
    0.57
    and
    0.55
     symmetries
    0.54
     perturbative
    0.54
     regimes
    0.54
     mathematical
    0.53
    Act Density 0.092%

    No Known Activations