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

    Neuronpedia

    INDEX
    Explanations

    as a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Blush
    0.31
    ly
    0.29
     at
    0.29
     Paper
    0.29
     Shader
    0.29
    /
    0.29
     Pork
    0.29
     Bals
    0.29
     blushed
    0.29
     P
    0.28
    POSITIVE LOGITS
    在
    0.44
    و
    0.40
    Mientras
    0.37
    Türkiye
    0.33
    admins
    0.33
    ে
    0.33
    ใน
    0.33
     ਅਤੇ
    0.33
    と
    0.33
    的
    0.32
    Act Density 4.799%

    No Known Activations