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

    Neuronpedia

    INDEX
    Explanations

    code structure and syntax elements commonly found in programming languages

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

    "name" or similar variations

    np_acts-logits-general · gemini-2.0-flash

    name attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Titles
    -0.71
    Titles
    -0.66
     oprot
    -0.61
     سكانية
    -0.61
    RectangleBorder
    -0.59
     Wiktionnaire
    -0.58
    发表于
    -0.57
     titles
    -0.57
    ReusableCell
    -0.57
    abestanden
    -0.56
    POSITIVE LOGITS
    name
    1.37
     name
    1.25
    Name
    0.64
    neme
    0.62
    NameValuePair
    0.62
    namefont
    0.61
     nationaux
    0.61
     nam
    0.59
     na
    0.58
    na
    0.58
    Act Density 0.083%

    No Known Activations