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

    Neuronpedia

    INDEX
    Explanations

    references to URLs or web addresses in the text

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

    URLs for web content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.53
    Diwedd
    -0.50
    masing
    -0.47
    الدراسه
    -0.45
     FixedUpdate
    -0.45
    })),
    -0.44
    mergeFrom
    -0.44
    DataSetChanged
    -0.43
    ))))))))
    -0.43
     black
    -0.43
    POSITIVE LOGITS
    url
    1.33
     url
    1.30
    Url
    1.10
     URL
    1.08
    setUrl
    1.02
    URL
    1.01
    getUrl
    1.00
     Url
    0.95
    urls
    0.91
     urls
    0.91
    Act Density 0.009%

    No Known Activations