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

    Neuronpedia

    INDEX
    Explanations

    words related to work situations like jobs, career, insurance, and teamwork

    oai_token-act-pair · gemini-2.0-flash

    employee and employer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SESSION
    -0.50
    testnet
    -0.43
     chí
    -0.42
     extradition
    -0.41
    laise
    -0.41
     Session
    -0.41
     Astrophysical
    -0.41
    bernador
    -0.41
     session
    -0.41
    asyarakat
    -0.40
    POSITIVE LOGITS
     employee
    1.67
     employees
    1.60
     Employee
    1.53
     employers
    1.48
     Employees
    1.46
     employer
    1.46
    employee
    1.42
    Employees
    1.42
    Employee
    1.38
     workplace
    1.38
    Act Density 16.236%

    No Known Activations