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

    Neuronpedia

    INDEX
    Explanations

    used extensively or widely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আপনার
    0.90
    あなたの
    0.87
    আপনি
    0.83
     einfachen
    0.83
    自分の
    0.83
     conseguido
    0.82
     ধরনের
    0.82
     causado
    0.82
     señalado
    0.82
    したいと思います
    0.81
    POSITIVE LOGITS
     extensively
    1.54
     throughout
    1.43
     alongside
    1.41
     elsewhere
    1.37
     prominently
    1.31
     during
    1.23
     widely
    1.21
     externally
    1.19
     worldwide
    1.15
     everywhere
    1.15
    Act Density 0.873%

    No Known Activations