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

    Neuronpedia

    INDEX
    Explanations

    words related to parsing JSON code and moving files

    oai_token-act-pair · gemini-2.0-flash

    parsed JSON functions and error handling in code

    np_token-act-pair-logits · gpt-4o-mini

    Code parsing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ://$
    -0.52
     "
    -0.47
     “
    -0.46
     off
    -0.45
    ,
    -0.42
     am
    -0.41
     &
    -0.41
     #
    -0.40
     Ad
    -0.40
    อย่างไร
    -0.39
    POSITIVE LOGITS
    uxxxx
    0.92
     itſelf
    0.87
     okuyayım
    0.85
     greateſt
    0.81
     Efq
    0.80
     विश्वसनीयता
    0.79
     ſta
    0.79
     Perſ
    0.78
     perfons
    0.78
     raiſ
    0.77
    Act Density 2.256%

    No Known Activations