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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and function calls in programming

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

    programming output and debugging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.88
     AssemblyCulture
    -0.80
    GEBURTSDATUM
    -0.77
    majánló
    -0.76
    DockStyle
    -0.76
     незавершена
    -0.75
     ujednoznacz
    -0.73
     صوتيه
    -0.71
     kasarigan
    -0.70
    Personendaten
    -0.70
    POSITIVE LOGITS
     "
    0.33
    ,
    0.33
     
    0.33
     full
    0.32
     said
    0.29
     assure
    0.28
     underlined
    0.28
    :
    0.28
     underline
    0.28
     un
    0.27
    Act Density 0.010%

    No Known Activations