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

    Neuronpedia

    INDEX
    Explanations

    business service and value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     linguistics
    0.49
     syntax
    0.46
     voxel
    0.46
     neurons
    0.43
     analyzer
    0.43
     leukemia
    0.43
     module
    0.43
     analysis
    0.42
     senescence
    0.42
     analyze
    0.41
    POSITIVE LOGITS
     Hotels
    0.58
     होटल
    0.57
     overpriced
    0.54
     disappointment
    0.54
     disappointments
    0.53
    hotels
    0.52
     услуги
    0.51
    Restaurants
    0.50
     restaurantes
    0.50
     TripAdvisor
    0.50
    Act Density 0.023%

    No Known Activations