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

    Neuronpedia

    INDEX
    Explanations

    references to supplementary materials and publications

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

    LaTeX math mode formatting

    np_acts-logits-general · gemini-2.0-flash

    special characters and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -1.00
    IsContent
    -0.85
     الحره
    -0.79
     tartalomajánló
    -0.78
     resourceCulture
    -0.78
     виправивши
    -0.77
    __':
    -0.77
     مشين
    -0.76
     "}";
    -0.76
    "){
    -0.75
    POSITIVE LOGITS
    <strong>
    1.21
    <b>
    1.20
    //
    1.09
     **
    0.89
    mathbf
    0.73
     //
    0.73
    <!--
    0.71
    **
    0.61
    boldsymbol
    0.56
     \
    0.56
    Act Density 0.425%

    No Known Activations