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

    Neuronpedia

    INDEX
    Explanations

    instances of the markup or structural elements in a document

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

    Welcome, Q, goog, Cut

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     but
    -0.57
     n
    -0.50
     plus
    -0.48
     so
    -0.47
     then
    -0.46
     up
    -0.46
     une
    -0.45
    なら
    -0.45
    شاركة
    -0.44
     la
    -0.44
    POSITIVE LOGITS
     للاسماء
    1.10
     <=",
    1.03
     ſtand
    0.94
     uſe
    0.91
    новниш
    0.88
     ſta
    0.88
     houſe
    0.88
    ագրություններ
    0.87
     متعلقه
    0.87
     ErrIntOverflow
    0.86
    Act Density 0.044%

    No Known Activations