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

    Neuronpedia

    INDEX
    Explanations

    technical and linguistic concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demonstrating
    0.47
     demonstrated
    0.45
     props
    0.40
     abs
    0.38
     commented
    0.37
     בפ
    0.37
    (
    0.37
     explicitly
    0.37
     greater
    0.37
    िटी
    0.36
    POSITIVE LOGITS
    xcodep
    0.40
     ස්ථා
    0.40
    股份有限公司
    0.40
    ỉnh
    0.39
    ന്ധി
    0.39
    scalable
    0.38
     Ağ
    0.38
    ᐋ
    0.38
    mbH
    0.38
    关闭
    0.38
    Act Density 0.000%

    No Known Activations