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

    Neuronpedia

    INDEX
    Explanations

    job title or position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     company
    0.46
    company
    0.45
     empresa
    0.44
     perusahaan
    0.44
     empresas
    0.43
     Rolex
    0.43
     Accenture
    0.43
     companies
    0.42
    公司
    0.42
     corporate
    0.41
    POSITIVE LOGITS
    deadline
    0.43
    Deadline
    0.42
     نیند
    0.42
    ুষ
    0.41
    க்கிறது
    0.40
    èrement
    0.39
     kyun
    0.39
    Guided
    0.38
     runs
    0.38
    utérus
    0.38
    Act Density 0.008%

    No Known Activations