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

    Neuronpedia

    INDEX
    Explanations

    commands and function calls in a programming context

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

    commands after others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setArguments
    -0.44
     سكانية
    -0.43
    期刊论文
    -0.38
    
    -0.36
    例文帳に追加
    -0.35
    Diweddarwch
    -0.35
    TagMode
    -0.34
    ValueStyle
    -0.34
     Winaray
    -0.33
    classnames
    -0.32
    POSITIVE LOGITS
     afterwards
    0.65
    +#+#
    0.61
     afterward
    0.60
     Daarna
    0.60
     subsequently
    0.59
     потім
    0.59
     Afterwards
    0.59
     Danach
    0.57
     anschließend
    0.57
     thereafter
    0.57
    Act Density 0.043%

    No Known Activations