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

    Neuronpedia

    INDEX
    Explanations

    function and method signatures in code

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

    Code snippets ending in closing curly brackets/parenthesis

    np_acts-logits-general · gemini-2.0-flash

    code parsing and structuring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stdc
    -0.62
    ():
    -0.55
    '||
    -0.54
    ioutil
    -0.54
    <>
    -0.54
    `;
    -0.52
    sidemargin
    -0.51
    '];
    -0.51
    -0.51
    HomeAsUpEnabled
    -0.51
    POSITIVE LOGITS
     {
    0.67
    تقاوى
    0.61
    ViewFeatures
    0.61
    AutoScaleMode
    0.60
     FishBase
    0.57
     throws
    0.56
    hyrchwyd
    0.56
    enderror
    0.52
     الاطلاع
    0.50
     Polícia
    0.50
    Act Density 0.063%
    No Known Activations