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

    Neuronpedia

    INDEX
    Explanations

    travel passes and discounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Responses
    0.49
     அறி
    0.44
    Reasoner
    0.43
     संवेदना
    0.42
    ประส
    0.42
    localized
    0.41
     Erkennt
    0.41
    results
    0.41
    ResponseMessage
    0.41
    Object
    0.40
    POSITIVE LOGITS
     ticket
    0.66
     prepaid
    0.66
     tickets
    0.66
     अनलिमिटेड
    0.63
     discounts
    0.63
     bigli
    0.62
     tarifas
    0.61
     entitlements
    0.60
     tarifs
    0.60
     प्रीपेड
    0.60
    Act Density 0.055%

    No Known Activations