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

    Neuronpedia

    INDEX
    Explanations

    references to URLs or URL-related data

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

    URLs in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    scalatest
    -0.53
     mierda
    -0.52
     argint
    -0.46
    entlicher
    -0.45
    enskap
    -0.45
    حياته
    -0.45
    bufio
    -0.44
     ffilmiau
    -0.44
    колеп
    -0.44
    chränk
    -0.44
    POSITIVE LOGITS
    URL
    2.61
     URL
    1.85
    URLs
    1.42
     URLs
    1.33
    NSURL
    1.13
     Url
    0.97
    Url
    0.92
    URLException
    0.91
     baseURL
    0.85
     url
    0.82
    Act Density 0.004%

    No Known Activations