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

    Neuronpedia

    INDEX
    Explanations

    LaTeX commands for mathematical equations.

    oai_token-act-pair · gemini-2.0-flash

    backslashes and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    новниш
    -0.80
    expandindo
    -0.78
     ligiloj
    -0.78
    queles
    -0.77
    polazione
    -0.76
    BeginContext
    -0.76
     wearer
    -0.76
     idéia
    -0.75
     للمعارف
    -0.73
     Мексичка
    -0.73
    POSITIVE LOGITS
    </h2>
    0.62
     é
    0.60
    </em>
    0.59
    }\\
    0.58
    ”,
    0.58
    </strong>
    0.57
     $$
    0.57
    ape
    0.57
    тру
    0.56
    }}}{
    0.56
    Act Density 1.996%

    No Known Activations