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

    Neuronpedia

    INDEX
    Explanations

    salary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tissues
    -0.08
    ЎыџN
    -0.08
     measurement
    -0.07
     incon
    -0.07
     girdi
    -0.07
     markings
    -0.07
     currents
    -0.07
     treats
    -0.07
     checks
    -0.07
     reduced
    -0.06
    POSITIVE LOGITS
     salary
    0.17
     Salary
    0.13
    Salary
    0.12
     salaries
    0.12
    salary
    0.10
    _salary
    0.09
     Scarlet
    0.08
     Hillary
    0.07
     Sar
    0.07
     sä
    0.07
    Act Density 0.004%

    No Known Activations