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

    Neuronpedia

    INDEX
    Explanations

    sections that reference or link to additional resources or publications

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

    "References", "external links", and categories sections

    np_acts-logits-general · gemini-2.0-flash

    references and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.06
     purpoſe
    -1.02
     myſelf
    -1.02
     houſe
    -0.99
     Monfieur
    -0.95
     ſtate
    -0.95
     juſ
    -0.94
     themſelves
    -0.93
     greateſt
    -0.91
     ſever
    -0.91
    POSITIVE LOGITS
    :
    0.85
    ↵↵
    0.76
    <eos>
    0.74
    :✨
    0.72
    ↵
    0.68
     مشين
    0.67
     autorytatywna
    0.62
    GEBURTSDATUM
    0.61
     resourceCulture
    0.60
    </h2>
    0.60
    Act Density 0.148%

    No Known Activations