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

    Neuronpedia

    INDEX
    Explanations

    audience interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مدرسه
    0.63
     জন্
    0.63
    一支
    0.62
     এঁ
    0.62
     hormonal
    0.62
    idth
    0.61
    噗
    0.60
     ны
    0.59
    中使用
    0.58
    wen
    0.57
    POSITIVE LOGITS
     customers
    3.01
     consumers
    2.78
     users
    2.70
     Customers
    2.67
     고객
    2.65
    客户
    2.65
    Customers
    2.61
     customer
    2.60
    用户
    2.59
    消费者
    2.53
    Act Density 0.720%

    No Known Activations