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

    Neuronpedia

    INDEX
    Explanations

    There's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dû
    0.50
    這個
    0.46
    인이
    0.45
    된
    0.45
     thing
    0.45
    ølge
    0.45
    왼
    0.45
     straightforward
    0.45
    你
    0.44
     practice
    0.44
    POSITIVE LOGITS
    ਸ਼
    0.48
    abouts
    0.46
     אין
    0.45
     কখনোই
    0.44
     Asalamualaikum
    0.43
    ippings
    0.42
    inetics
    0.42
     유사
    0.42
    ਸ਼
    0.41
    𝒽
    0.41
    Act Density 0.026%

    No Known Activations