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

    Neuronpedia

    INDEX
    Explanations

    family by marriage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জল
    0.38
     නිර්
    0.38
     pylori
    0.37
     يناير
    0.36
     পাহাড়
    0.36
    こだ
    0.36
     oo
    0.35
    മുള്ള
    0.35
     ceb
    0.35
     eureka
    0.35
    POSITIVE LOGITS
     শ্বশুর
    1.23
     married
    1.14
     ससुराल
    1.11
     husbands
    1.04
    婿
    1.03
    媳
    0.99
     marries
    0.96
    駙
    0.96
    Married
    0.95
    married
    0.95
    Act Density 0.007%

    No Known Activations