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

    Neuronpedia

    INDEX
    Explanations

    structured academic or technical content

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

    Text found within HTML tags

    np_acts-logits-general · gemini-2.0-flash

    section titles or formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.88
     للاسماء
    -0.84
    Дереккөздер
    -0.84
    Referanser
    -0.80
    Cyfeiriadau
    -0.79
     nahilalakip
    -0.78
     يتيمه
    -0.77
    లాలు
    -0.75
     gyhoeddwyd
    -0.75
    tanleria
    -0.74
    POSITIVE LOGITS
    <strong>
    0.98
    <h3>
    0.89
    <b>
    0.84
    <h2>
    0.77
    <h4>
    0.68
    <u>
    0.65
    <h1>
    0.63
    <h5>
    0.58
    ###
    0.54
    ##
    0.52
    Act Density 0.523%

    No Known Activations