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

    Neuronpedia

    INDEX
    Explanations

    car issues and specs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     accommodations
    0.50
     licensure
    0.50
    neighbor
    0.48
    oriented
    0.44
     energized
    0.44
    maximize
    0.43
     coworker
    0.42
     resiliency
    0.41
     acetaminophen
    0.41
    Kra
    0.40
    POSITIVE LOGITS
     Vaux
    0.85
     motorway
    0.80
     adverts
    0.78
     UK
    0.77
     (£
    0.75
     £
    0.75
     fitted
    0.70
     postcode
    0.70
     Citro
    0.70
     specialist
    0.69
    Act Density 0.011%

    No Known Activations