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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas and parentheses

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

    closing parenthesis and code block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.63
    tvguidetime
    -0.57
     Paglinawan
    -0.56
    sidemargin
    -0.51
     deleteById
    -0.49
    ніципа
    -0.48
     khán
    -0.48
    FDRE
    -0.47
    EndInit
    -0.47
    ValueStyle
    -0.47
    POSITIVE LOGITS
     يتيمه
    0.54
    yntaxException
    0.41
     means
    0.39
     either
    0.39
    CPE
    0.34
    というと
    0.34
    旅行
    0.34
    ContentLoaded
    0.34
     detto
    0.34
    อะไร
    0.34
    Act Density 0.018%

    No Known Activations