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

    Neuronpedia

    INDEX
    Explanations

    late and overdue payments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویت
    0.39
    észet
    0.38
     stitched
    0.38
     congrat
    0.37
     излу
    0.37
     یخچال
    0.37
    azas
    0.37
    ignée
    0.37
    钾
    0.37
     Payload
    0.37
    POSITIVE LOGITS
     delinquent
    1.41
     delinquency
    1.40
     defaulted
    1.30
     unpaid
    1.28
     defaulting
    1.28
     overdue
    1.27
     delinqu
    1.24
     defaults
    1.22
     defaul
    1.22
    defaults
    1.11
    Act Density 0.022%

    No Known Activations