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

    Neuronpedia

    INDEX
    Explanations

    welcoming greetings and service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.88
    的公司
    0.76
     importe
    0.70
     montón
    0.69
     êtes
    0.68
    的样子
    0.68
    的服务
    0.68
     eignet
    0.68
     è
    0.68
    的路
    0.68
    POSITIVE LOGITS
    to
    1.04
    ین
    0.96
    em
    0.84
     ۵
    0.82
    ა
    0.82
     ۴
    0.79
    ید
    0.78
    at
    0.77
    ۶
    0.75
    ༨
    0.75
    Act Density 0.039%

    No Known Activations