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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references

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

    compared with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.45
    sizeCache
    -0.41
    apimachinery
    -0.40
     Мексичка
    -0.40
    afficheront
    -0.39
     समीक्षाओं
    -0.39
     ویکی‌پدی
    -0.38
    PropertyChanging
    -0.38
     actionTypes
    -0.36
     للاسماء
    -0.36
    POSITIVE LOGITS
     Administrativna
    0.47
     يتيمه
    0.47
    原始内容存档于
    0.46
     informativo
    0.45
    әрмәләр
    0.44
    eseorang
    0.44
     loading
    0.43
     surla
    0.43
     الاطلاع
    0.43
    ativna
    0.42
    Act Density 0.110%

    No Known Activations