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

    Neuronpedia

    INDEX
    Explanations

    technical terms and formats related to programming or scripting languages

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

    Code, paths, or versions

    np_acts-logits-general · gemini-2.0-flash

    variable assignments and template literals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.96
    ↵↵↵
    -0.74
    {}".
    -0.71
    </strong>
    -0.67
    ↵↵↵↵↵
    -0.54
     {}".
    -0.53
    {:
    -0.53
    ;)
    -0.53
    ']").
    -0.51
    ">
    -0.51
    POSITIVE LOGITS
     ${
    2.15
    ${
    2.14
    (${
    1.79
    /${
    1.77
    -${
    1.75
    :${
    1.73
    .${
    1.72
     '${
    1.71
    =${
    1.66
    _${
    1.62
    Act Density 0.115%

    No Known Activations