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

    Neuronpedia

    INDEX
    Explanations

    imaginary part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulating
    0.50
     reusable
    0.42
     電動
    0.41
    istage
    0.40
    тировать
    0.39
    ately
    0.38
     রায়
    0.38
    riek
    0.38
    。</
    0.38
    atable
    0.37
    POSITIVE LOGITS
    quadratic
    0.51
     quadratic
    0.46
     Quadratic
    0.44
     quadrat
    0.43
    താ
    0.42
    چال
    0.41
    Invest
    0.41
     quadrad
    0.41
    ವಹ
    0.41
     মুশ
    0.40
    Act Density 0.000%

    No Known Activations