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

    Neuronpedia

    INDEX
    Explanations

    programming and coding terminology related to version control systems

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

    code, html, or math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ivelany
    -0.61
    تفصیلات
    -0.61
    Datuak
    -0.58
     ]];
    -0.54
     Tatsache
    -0.54
     voordeel
    -0.54
    '));
    -0.53
    رشف
    -0.50
    AppMethodBeat
    -0.50
     TAMBIÉN
    -0.48
    POSITIVE LOGITS
    <th>
    2.45
    <h1>
    0.74
    <h4>
    0.70
    <u>
    0.66
    <h2>
    0.66
    __(/*!
    0.65
    <h5>
    0.60
    ［
    0.59
     &[
    0.57
    <table>
    0.57
    Act Density 0.001%

    No Known Activations