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

    Neuronpedia

    INDEX
    Explanations

    indicators or metrics related to probability or statistical significance

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

    Code snippets or file paths

    np_acts-logits-general · gemini-2.0-flash

    code punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.71
    OGND
    -0.65
    ")));
    -0.63
    "])
    -0.63
    ":
    -0.63
    )");
    -0.62
     """
    -0.61
    '):
    -0.61
    "]);
    -0.61
    `;
    -0.60
    POSITIVE LOGITS
    ['
    1.27
    [
    1.26
    ["
    1.25
    .
    1.17
    ._
    0.97
    ["_
    0.88
    ['_
    0.83
    ()[
    0.83
    ().
    0.83
    .[
    0.80
    Act Density 0.267%

    No Known Activations