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

    Neuronpedia

    INDEX
    Explanations

    ellipses or omissions in text

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

    "**" followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.92
    gulier
    -0.57
    ization
    -0.57
     rodin
    -0.55
    Marin
    -0.54
    AddHtmlAttribute
    -0.54
     Photocase
    -0.53
    ReusableCell
    -0.53
    ‏‏
    -0.52
    Portail
    -0.51
    POSITIVE LOGITS
    s
    0.56
    rupulous
    0.48
     rodríguez
    0.47
     checkBox
    0.47
    grès
    0.46
    CHAPTER
    0.45
    Välislingid
    0.43
     CWE
    0.42
     Berikut
    0.42
    posób
    0.42
    Act Density 0.018%

    No Known Activations