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

    Neuronpedia

    INDEX
    Explanations

    expenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Noz
    0.63
    ция
    0.61
     काल
    0.58
     Socialist
    0.57
     symbol
    0.56
    льность
    0.55
    性は
    0.54
    ۳
    0.54
     XVI
    0.54
     siglos
    0.54
    POSITIVE LOGITS
     расходы
    1.08
     expenses
    1.04
     расходов
    1.02
     dépenses
    0.95
     costs
    0.89
     Expenses
    0.89
     spese
    0.88
    expenses
    0.88
     expenditures
    0.87
     gastos
    0.86
    Act Density 0.095%

    No Known Activations