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

    Neuronpedia

    INDEX
    Explanations

    entity recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    1.23
    ು
    1.20
    ه‌
    1.19
    ();}
    1.19
    다는
    1.18
     OSX
    1.17
    দের
    1.15
    ";}
    1.14
    )‏
    1.13
    ه‌ای
    1.13
    POSITIVE LOGITS
     fearless
    1.27
    ز
    1.17
     schnell
    1.14
    టర్
    1.14
     möjligt
    1.10
    ن
    1.09
    スプレイ
    1.09
     właśnie
    1.08
     perbedaan
    1.08
     wynika
    1.08
    Act Density 0.124%

    No Known Activations