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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACKET
    -0.08
     daardoor
    -0.08
     sifat
    -0.07
    -functional
    -0.07
    ೀಯ
    -0.07
    ्यक्ष
    -0.07
    koch
    -0.07
    ushu
    -0.07
     ವಿಧಾನ
    -0.07
    蒲
    -0.07
    POSITIVE LOGITS
    确认
    0.11
     확인
    0.10
    確認
    0.09
     dort
    0.09
     confirmation
    0.08
    <strong
    0.08
     confirming
    0.07
    Confirmation
    0.07
     entries
    0.07
    'il
    0.07
    Act Density 0.083%

    No Known Activations