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

    Neuronpedia

    INDEX
    Explanations

    instances of escape characters and syntax delimiters in code

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

    file paths and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.46
    jspb
    -0.38
     FetchType
    -0.35
    <bos>
    -0.33
     rostros
    -0.33
     autobuses
    -0.33
    dflare
    -0.31
     Buses
    -0.31
     Maritime
    -0.31
    Buses
    -0.31
    POSITIVE LOGITS
     snippetHide
    0.66
     Réponses
    0.63
    المشاركات
    0.59
    最快更新
    0.56
     لينك
    0.54
    NameInMap
    0.52
    +#+
    0.51
    ngdoc
    0.50
     <=",
    0.50
    enumii
    0.49
    Act Density 0.063%

    No Known Activations