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

    Neuronpedia

    INDEX
    Explanations

    references to filenames within the document

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

    filename and hostname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    -0.51
    3
    -0.50
    AndGet
    -0.50
     Super
    -0.49
    StrictEqual
    -0.48
    AndSet
    -0.48
    4
    -0.48
    CURLOPT
    -0.48
    I
    -0.48
    Билгалдахарш
    -0.46
    POSITIVE LOGITS
    Filename
    1.24
     Filename
    1.13
     filename
    1.07
    filename
    1.02
    FILENAME
    0.89
     filenames
    0.88
    FileName
    0.87
    文件名
    0.74
     FileName
    0.73
     fileName
    0.71
    Act Density 0.006%

    No Known Activations