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

    Neuronpedia

    INDEX
    Explanations

    build

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ে
    1.21
    e
    1.01
    ozo
    0.94
    र्दू
    0.94
    疑
    0.93
    意
    0.89
    此之外
    0.89
     meaningful
    0.87
    ه
    0.87
     stable
    0.87
    POSITIVE LOGITS
    अप
    1.17
    สรร
    1.16
     erected
    1.15
     roads
    1.14
     dựng
    1.13
     up
    1.12
     elevators
    1.10
    ट
    1.09
     lancement
    1.09
     Umsetzung
    1.09
    Act Density 0.055%

    No Known Activations