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

    Neuronpedia

    INDEX
    Explanations

    references to preprints from the arXiv repository

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

    "arXiv" followed by a code

    np_acts-logits-general · gemini-2.0-flash

    arXiv preprints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -1.17
    FormTagHelper
    -0.82
    mybatisplus
    -0.79
     المعيارى
    -0.79
    Хьажоргаш
    -0.73
     aDecoder
    -0.72
     Administrativna
    -0.70
     esternos
    -0.69
    interopRequire
    -0.68
    RegistryLite
    -0.68
    POSITIVE LOGITS
    arXiv
    3.88
     arXiv
    1.17
    arxiv
    0.97
    Xiv
    0.64
    发表于
    0.56
     arxiv
    0.54
    filepath
    0.54
     EconPapers
    0.49
     squ
    0.47
    doi
    0.46
    Act Density 0.015%

    No Known Activations