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

    Neuronpedia

    INDEX
    Explanations

    costs and expenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wealth
    0.91
    wealth
    0.90
    Wealth
    0.83
    Powerful
    0.82
    Sing
    0.73
     powerful
    0.71
     wealthy
    0.71
     Wealth
    0.70
     backed
    0.70
    Uz
    0.70
    POSITIVE LOGITS
     costs
    2.23
     expenses
    2.13
     Costs
    2.02
     fees
    1.95
    Costs
    1.93
     Expenses
    1.91
    costs
    1.90
     Fees
    1.80
     COSTS
    1.78
    expenses
    1.73
    Act Density 0.482%

    No Known Activations