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

    Neuronpedia

    INDEX
    Explanations

    my experience and skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     profession
    0.97
     pensions
    0.97
     careers
    0.94
     career
    0.93
     pension
    0.92
     emeritus
    0.91
     himself
    0.89
     professions
    0.88
     retirement
    0.88
     professional
    0.87
    POSITIVE LOGITS
    Using
    1.00
     使用
    0.96
     사용
    0.94
    ijdens
    0.92
    Durante
    0.87
    ىن
    0.86
    ǐ
    0.85
     생성
    0.85
    を使用
    0.85
    Improved
    0.85
    Act Density 0.087%

    No Known Activations