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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associated structures in text

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

    Surrounding punctuation or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    code delimiters like `( ) [ ] " '`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (‘
    -0.60
    IndentedString
    -0.58
    RenderAtEndOf
    -0.57
    AntiForgeryToken
    -0.56
    =('
    -0.54
    =’
    -0.51
    (“
    -0.49
    ('/
    -0.48
    (__('
    -0.47
     vasca
    -0.47
    POSITIVE LOGITS
     "",
    0.79
    ​,
    0.79
    [],
    0.77
     resourceCulture
    0.73
     [],
    0.72
    '',
    0.71
     []).
    0.70
    %",
    0.67
     {},
    0.66
    下载附件
    0.66
    Act Density 0.102%

    No Known Activations