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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles hosted on arXiv

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

    arXiv preprints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.53
    SharedCtor
    -0.46
    FieldBuilder
    -0.45
    تقاوى
    -0.44
    tagHelperRunner
    -0.43
     Chwiliwch
    -0.43
    findpost
    -0.43
    出版年
    -0.42
    terase
    -0.41
    
    -0.40
    POSITIVE LOGITS
     arXiv
    1.66
    arxiv
    1.58
    arXiv
    1.19
     arxiv
    1.16
    Xiv
    0.96
     Arxiv
    0.84
     ARXIV
    0.80
     preprint
    0.54
    ietf
    0.49
     cosmic
    0.48
    Act Density 0.009%

    No Known Activations