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

    Neuronpedia

    INDEX
    Explanations

    errors related to system processes and logging activities

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

    Code snippets and URLs

    np_acts-logits-general · gemini-2.0-flash

    urls and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     •
    -0.92
    ,"
    -0.82
    ↵↵↵
    -0.74
    •
    -0.72
    <eos>
    -0.69
    ),"
    -0.67
    <strong>
    -0.63
    "—
    -0.59
    //
    -0.57
    "
    -0.56
    POSITIVE LOGITS
     ${
    1.51
     `
    1.48
    ${
    1.43
    `,
    1.42
    `;
    1.33
    `
    1.32
    "`
    1.27
     `;
    1.26
     `${
    1.26
    })`
    1.24
    Act Density 0.265%

    No Known Activations