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

    Neuronpedia

    INDEX
    Explanations

    remote work options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Employers
    0.61
    Hourly
    0.59
    Workspace
    0.58
    Employer
    0.57
     workplaces
    0.55
    加班
    0.55
    远程
    0.54
    employer
    0.54
     вечер
    0.50
     daylight
    0.50
    POSITIVE LOGITS
     Eligible
    0.52
     eligible
    0.50
     three
    0.45
     eligibility
    0.45
    Elig
    0.42
    eligible
    0.42
    地位
    0.41
    三天
    0.41
     Eligibility
    0.39
     mesto
    0.39
    Act Density 0.006%

    No Known Activations