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

    Neuronpedia

    INDEX
    Explanations

    employees and clones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ciudades
    0.91
     villes
    0.80
     cities
    0.79
     Ländern
    0.77
     ഇന്ത്യ
    0.77
     países
    0.75
     исче
    0.75
     montaña
    0.75
     городов
    0.75
     puoi
    0.73
    POSITIVE LOGITS
     employees
    1.51
     employee
    1.47
    员工
    1.43
    Employee
    1.41
    employee
    1.38
    employees
    1.34
     직원
    1.29
     Employee
    1.28
    員工
    1.27
     karyawan
    1.25
    Act Density 0.591%

    No Known Activations