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

    Neuronpedia

    INDEX
    Explanations

    code structure elements such as class definitions and methods in a programming context

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

    default or empty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.65
     Italijanski
    -0.62
     Италијани
    -0.57
     Signalez
    -0.56
    makeText
    -0.55
    findpost
    -0.54
     мәкал
    -0.54
    +#+#
    -0.52
     EClass
    -0.48
     ModelExpression
    -0.48
    POSITIVE LOGITS
     empty
    0.97
     default
    0.88
    empty
    0.86
     Empty
    0.83
    Empty
    0.81
    default
    0.79
     blank
    0.75
     leeren
    0.69
    EMPTY
    0.67
     EMPTY
    0.67
    Act Density 0.009%

    No Known Activations