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

    Neuronpedia

    INDEX
    Explanations

    wages and salary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     colonne
    0.68
    wości
    0.66
    クロマト
    0.66
     ವ್ಯ
    0.63
    oculars
    0.63
     foaf
    0.62
    রন
    0.61
    ్రహ్
    0.61
    濃
    0.61
     यूजर्स
    0.60
    POSITIVE LOGITS
     wages
    2.10
     wage
    1.85
     Wages
    1.64
     pay
    1.63
    wage
    1.49
    Wage
    1.49
     Wage
    1.47
     overtime
    1.45
     salary
    1.45
     salaries
    1.44
    Act Density 0.165%

    No Known Activations