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

    Neuronpedia

    INDEX
    Explanations

    helplines and phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    保証
    0.90
     اجر
    0.78
     اجرا
    0.72
    诖
    0.65
     “‘
    0.64
     ر
    0.62
    ใช้ง
    0.62
    酒
    0.62
     ഉപ
    0.62
     Gambling
    0.62
    POSITIVE LOGITS
     Tencent
    0.78
     mosques
    0.76
     separat
    0.75
     supermarkets
    0.74
     naszego
    0.73
     tens
    0.72
     स्थानीय
    0.72
     hundreds
    0.72
    시아
    0.71
    0.71
    Act Density 0.288%

    No Known Activations