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

    Neuronpedia

    INDEX
    Explanations

    vacation time and service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subsidies
    1.11
     subsidy
    1.06
     refunds
    0.99
    ّى
    0.98
     voucher
    0.95
     subsidized
    0.94
     Income
    0.94
     defray
    0.93
     offres
    0.93
     Multimedia
    0.92
    POSITIVE LOGITS
    matmul
    1.12
    า
    1.12
    kannya
    1.00
    m
    0.97
     घिरा
    0.97
    માં
    0.96
     oamen
    0.94
    হরে
    0.90
     tasked
    0.89
    মানে
    0.89
    Act Density 0.007%

    No Known Activations