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

    Neuronpedia

    INDEX
    Explanations

    pay, wages, salary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    入手
    1.03
    )\
    0.99
     qubits
    0.98
    x
    0.96
    $.
    0.96
    $
    0.96
    }$-
    0.95
    ak
    0.94
    /\
    0.93
    ∣
    0.92
    POSITIVE LOGITS
     wages
    1.37
     Wage
    1.34
     Wages
    1.26
     wage
    1.23
    Wage
    1.23
     salaries
    1.21
     Employees
    1.21
     pensions
    1.21
     праців
    1.20
     Employee
    1.11
    Act Density 0.273%

    No Known Activations