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

    Neuronpedia

    INDEX
    Explanations

    reducing costs and storage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kehad
    0.39
    urbed
    0.38
    ປະກ
    0.37
     terbuka
    0.35
     assurances
    0.35
     considère
    0.35
     ადამიან
    0.35
     सोसाइटी
    0.35
    nict
    0.34
     assuring
    0.34
    POSITIVE LOGITS
     rispar
    1.09
    节省
    1.06
     ahorrar
    1.03
     ahorro
    0.96
     reduce
    0.93
     reduces
    0.88
    Reduce
    0.85
    减少
    0.84
     reducing
    0.84
    reduce
    0.83
    Act Density 0.474%

    No Known Activations