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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to functions, tasks, and their management in programming contexts

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

    Code formatting or special characters

    np_acts-logits-general · gemini-2.0-flash

    formatted strings with seconds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    `);
    -1.67
    "];
    -1.58
    ']);
    -1.54
    }`);
    -1.52
    '];
    -1.51
    "]);
    -1.47
    ]");
    -1.44
    ");
    -1.44
    '];
    -1.44
    ]');
    -1.42
    POSITIVE LOGITS
     {}".
    1.46
     {}
    1.33
    {}".
    1.29
     {}'.
    1.27
     {}\
    1.27
    {}{}
    1.21
    {}/
    1.20
     "{}
    1.19
    {}
    1.17
    {}'.
    1.17
    Act Density 0.114%

    No Known Activations