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

    Neuronpedia

    INDEX
    Explanations

    code elements, particularly related to string manipulation, requests, and data structures

    oai_token-act-pair · gemini-2.0-flash

    strings, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.71
     Waray
    -0.62
     становника
    -0.60
     Wicidata
    -0.58
    ########.
    -0.57
     simulates
    -0.56
     tested
    -0.56
     Tested
    -0.55
     simulate
    -0.55
     Photocase
    -0.54
    POSITIVE LOGITS
    gna
    0.43
     over
    0.43
    ériques
    0.42
    surate
    0.41
    <bos>
    0.40
     color
    0.40
    mapreduce
    0.40
    WriteLiteral
    0.40
     bese
    0.39
     Outlook
    0.39
    Act Density 8.791%

    No Known Activations