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

    Neuronpedia

    INDEX
    Explanations

    elements and their attributes in a structured data format

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

    numbers and code fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.66
    VYMaps
    -0.61
    UserScript
    -0.56
    SharedCtor
    -0.55
    ंदीखरीदारी
    -0.53
    "]]
    -0.53
    Бахар
    -0.53
     autorytatywna
    -0.52
     '',
    -0.52
    '],
    -0.52
    POSITIVE LOGITS
     Pferd
    0.42
     évêque
    0.35
     desierto
    0.34
    เทศ
    0.34
    Outcomes
    0.33
     langues
    0.33
     coucher
    0.33
     ๆ
    0.33
     commandement
    0.32
     administratif
    0.32
    Act Density 0.060%

    No Known Activations