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

    Neuronpedia

    INDEX
    Explanations

    keywords and structure related to programming or coding languages

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

    code parsing and generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nawr
    -0.42
    Fech
    -0.36
     kenn
    -0.33
    erdo
    -0.33
    MLLoader
    -0.33
     fometimes
    -0.32
     horm
    -0.32
     absorbed
    -0.31
     animal
    -0.31
     tomb
    -0.30
    POSITIVE LOGITS
    
    0.64
    ########.
    0.63
     intptr
    0.62
     виправивши
    0.60
     resourceCulture
    0.59
    تفصیلات
    0.59
    uxxxx
    0.59
    parsedMessage
    0.59
    rawDesc
    0.58
     
    0.56
    Act Density 0.305%

    No Known Activations