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

    Neuronpedia

    INDEX
    Explanations

    elements and options related to selection or choices in programming contexts

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

    zzzz completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſind
    -0.74
     فريبيس
    -0.74
    iſen
    -0.72
    
    -0.70
     imagui
    -0.70
    ésultats
    -0.69
    niſſe
    -0.69
    ੝
    -0.69
    ſſung
    -0.69
    <unused41>
    -0.68
    POSITIVE LOGITS
     dieux
    0.30
     Bélgica
    0.24
     others
    0.24
     defStyle
    0.24
     cheval
    0.24
     preghiera
    0.23
    出
    0.23
     Belgien
    0.23
     patata
    0.23
     supper
    0.23
    Act Density 0.082%

    No Known Activations