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

    Neuronpedia

    INDEX
    Explanations

    specific names, terms, and references related to various fields, including science, technology, and culture

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

    Tokens before "et", company names, or names

    np_acts-logits-general · gemini-2.0-flash

    names followed by titles or companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ZZZ
    -0.67
     Paglinawan
    -0.66
     azi
    -0.65
    Benzo
    -0.65
    Datuak
    -0.65
    Koz
    -0.62
    izability
    -0.61
     Wiz
    -0.60
     Taz
    -0.59
     kasarigan
    -0.59
    POSITIVE LOGITS
     Dunham
    0.54
    <h1>
    0.52
     Pelham
    0.48
    ham
    0.46
     Cordero
    0.44
    ```
    0.44
     hodně
    0.43
     Gonçalves
    0.43
     těch
    0.43
     neler
    0.42
    Act Density 2.055%

    No Known Activations