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

    Neuronpedia

    INDEX
    Explanations

    punctuation and programming syntax elements

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

    read following <

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.44
     Eisenberg
    -0.39
    bootstrapcdn
    -0.38
     Cowan
    -0.36
    WebServlet
    -0.36
     Oskar
    -0.35
     Dodson
    -0.35
    principalColumn
    -0.35
     tem
    -0.35
    Premise
    -0.35
    POSITIVE LOGITS
     reading
    1.27
     Reading
    1.19
    Reading
    1.16
    reading
    1.15
     READING
    1.09
     reader
    1.03
     read
    0.98
     lectura
    0.98
     Reads
    0.97
     reads
    0.96
    Act Density 0.054%

    No Known Activations