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

    Neuronpedia

    INDEX
    Explanations

    helpline phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     xong
    0.41
    ળ
    0.38
    originalname
    0.38
     我们
    0.37
     ហើយ
    0.37
     contradict
    0.37
    ˏ
    0.37
     মূল
    0.36
    穩定
    0.36
     แล้ว
    0.36
    POSITIVE LOGITS
    Phone
    0.93
     phone
    0.91
     Phone
    0.89
     전화
    0.88
    電話
    0.86
     telephone
    0.83
    电话
    0.82
     телефон
    0.81
    phone
    0.81
     ফোন
    0.81
    Act Density 0.019%

    No Known Activations