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

    Neuronpedia

    INDEX
    Explanations

    key performance indicators and data evaluation phrases

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

    colon followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.56
    脚注の使い方
    -0.47
    存于互联网档案馆
    -0.46
     Administrativna
    -0.43
     AssemblyProduct
    -0.43
    setObjectName
    -0.43
     للمعارف
    -0.42
     AssemblyCompany
    -0.41
    Datuak
    -0.41
    WebElementEntity
    -0.40
    POSITIVE LOGITS
    :
    0.54
    :.
    0.50
    :...
    0.50
    :?
    0.50
    :{}
    0.46
    ：
    0.46
    :*
    0.45
    :+
    0.44
    :_
    0.44
    :<
    0.44
    Act Density 0.121%

    No Known Activations