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

    Neuronpedia

    INDEX
    Explanations

    comments and notes in programming code related to error handling and implementation details

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

    Code snippets or programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    code comments and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ”—
    -0.95
    .”.
    -0.90
    )”.
    -0.88
    .”—
    -0.88
     ”.
    -0.84
    `;
    -0.84
    .’”
    -0.82
     .”
    -0.80
    <eos>
    -0.80
    ’.”
    -0.77
    POSITIVE LOGITS
     بيها
    0.80
     TODO
    0.78
     we
    0.76
     stuff
    0.72
     here
    0.70
    ↵
    0.68
      
    0.67
     daqui
    0.66
     ici
    0.65
     */
    0.65
    Act Density 0.869%

    No Known Activations