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

    Neuronpedia

    INDEX
    Explanations

    references and citations within a document

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

    Referring to numbered references or footnotes

    np_acts-logits-general · gemini-2.0-flash

    Category and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HandlerContext
    -0.66
    ContentAsync
    -0.64
    Handlung
    -0.59
     TAMBÉM
    -0.59
    Identyfik
    -0.58
    帖最后由
    -0.57
    Jeografia
    -0.57
     CreateTagHelper
    -0.57
    السكان
    -0.56
     متعلقه
    -0.55
    POSITIVE LOGITS
     references
    1.89
     References
    1.83
    references
    1.69
    References
    1.67
     reference
    1.57
     Reference
    1.53
    Reference
    1.43
    reference
    1.42
     notes
    1.40
     Notes
    1.36
    Act Density 1.229%

    No Known Activations