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

    Neuronpedia

    INDEX
    Explanations

    finite field polynomials algebraic groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.46
     Rounded
    0.41
    ண்டும்
    0.40
    现在
    0.39
    chyné
    0.39
    下面
    0.39
    न्दी
    0.38
    خود
    0.38
    褒
    0.38
    その他
    0.37
    POSITIVE LOGITS
    ]=\
    0.45
     waarin
    0.44
    ']);
    0.39
    큐
    0.37
    orp
    0.36
     waarop
    0.36
    apan
    0.35
     quelqu
    0.35
     box
    0.35
    ]$
    0.35
    Act Density 0.001%

    No Known Activations