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

    Neuronpedia

    INDEX
    Explanations

    George Meade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused301>
    0.55
    され
    0.49
    <unused354>
    0.48
    リ
    0.48
    же
    0.46
    <unused203>
    0.46
    鐏
    0.46
    <unused243>
    0.45
     sàng
    0.45
    <unused2049>
    0.45
    POSITIVE LOGITS
    an
    0.48
    0.45
     LANGUAGES
    0.41
    ↵↵
    0.41
    </h3>
    0.41
     Instructor
    0.40
     Outdoor
    0.39
     mundial
    0.39
     아니다
    0.39
     waxes
    0.39
    Act Density 0.000%

    No Known Activations