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

    Neuronpedia

    INDEX
    Explanations

    shops and restaurants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subspaces
    0.43
     ISBN
    0.42
     Pennsylvania
    0.42
    세대
    0.41
     vulnerabilities
    0.41
     son
    0.41
     Generating
    0.40
     sequestration
    0.39
     unpublished
    0.38
     nuclear
    0.38
    POSITIVE LOGITS
     магази
    0.66
     рестора
    0.61
     shops
    0.59
    shopping
    0.59
    Shopping
    0.59
     shopping
    0.58
    shops
    0.58
     दुकानें
    0.55
     restaurantes
    0.55
     tiendas
    0.55
    Act Density 0.041%

    No Known Activations