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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotation marks

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

    accessing files and environment variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.58
    Према
    -0.52
    الحياه
    -0.51
    verwijspagina
    -0.50
    itness
    -0.49
    transQ
    -0.44
    UIControlState
    -0.43
    TokenNameDOT
    -0.42
    IUrlHelper
    -0.42
    Diweddarwch
    -0.41
    POSITIVE LOGITS
    ioutil
    0.55
    fstream
    0.49
    stdlib
    0.49
    cstdio
    0.48
    AccessFile
    0.42
    stdio
    0.40
    FileOutputStream
    0.40
     file
    0.40
     fopen
    0.39
     files
    0.39
    Act Density 0.000%

    No Known Activations