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

    Neuronpedia

    INDEX
    Explanations

    function definitions and return statements in code

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

    Code-related punctuation and keywords

    np_acts-logits-general · gemini-2.0-flash

    citations with fig

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jefus
    -0.77
     ་་
    -0.75
    )";
    -0.73
     Majefty
    -0.70
     myſelf
    -0.70
     Reſ
    -0.68
     Monfieur
    -0.67
    UnusedPrivate
    -0.67
     Efq
    -0.66
     SqlDbType
    -0.66
    POSITIVE LOGITS
     <
    1.02
    <>
    0.92
     <>
    0.88
    <
    0.77
     (<
    0.73
    (<
    0.63
     /*#__
    0.60
     (
    0.59
    <tr>
    0.51
    <h3>
    0.49
    Act Density 0.019%

    No Known Activations