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

    Neuronpedia

    INDEX
    Explanations

    data processor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تے
    1.85
     breathtaking
    1.85
    ەتی
    1.81
     vertebrate
    1.80
     グッチ
    1.80
     מאוד
    1.73
     bibliographic
    1.73
     transcoding
    1.70
    溘
    1.68
     sportsbook
    1.66
    POSITIVE LOGITS
    ي
    2.38
    ים
    2.09
    fö
    1.83
    करण
    1.81
    fondo
    1.78
    يًا
    1.72
    ٦
    1.69
    ი
    1.68
    י
    1.66
    falcon
    1.62
    Act Density 0.213%

    No Known Activations