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

    Neuronpedia

    INDEX
    Explanations

    Singapore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    1.88
    <0x80>
    1.70
    К
    1.68
     carbides
    1.67
    ни
    1.66
    О
    1.57
    {~
    1.55
     sonuc
    1.55
    ным
    1.45
    성화
    1.45
    POSITIVE LOGITS
    ている
    2.28
    ار
    2.11
    ra
    2.06
    د
    2.05
    tedir
    2.00
    თვის
    1.98
    نظر
    1.98
    ح
    1.98
     Seit
    1.93
    ্ধু
    1.91
    Act Density 0.015%

    No Known Activations