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

    Neuronpedia

    INDEX
    Explanations

    URLs and email addresses

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

    email addresses or website URLs

    np_acts-logits-general · gemini-2.0-flash

    links and contact info

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.83
     Derfor
    -0.79
     StatelessWidget
    -0.72
     conseguenza
    -0.72
     Daarom
    -0.69
    Spoljašnje
    -0.66
    ItemBackground
    -0.65
     مشين
    -0.65
     Савезне
    -0.65
     chré
    -0.65
    POSITIVE LOGITS
    Also
    0.62
     disambiguazione
    0.62
     Also
    0.61
    <eos>
    0.57
     Alternatively
    0.55
    Alternatively
    0.55
    Or
    0.53
    也可以
    0.53
     Or
    0.52
    ↵↵
    0.51
    Act Density 0.154%

    No Known Activations