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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their contexts in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Floating point numbers followed by more numbers

    np_acts-logits-general · gemini-2.0-flash

    "and, does"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Waray
    -0.48
    кульп
    -0.48
    bastien
    -0.45
    LEn
    -0.45
     __
    -0.45
    PARATUS
    -0.43
    :✨
    -0.43
    ➟
    -0.43
     zas
    -0.42
     slide
    -0.42
    POSITIVE LOGITS
    ");
    1.09
    ];
    1.06
    "];
    1.05
    '];
    1.03
    ";
    1.02
    "];
    1.01
    ]</
    0.98
    )";
    0.97
    ;</
    0.97
    ;\\
    0.97
    Act Density 0.289%

    No Known Activations