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

    Neuronpedia

    INDEX
    Explanations

    references to machine learning model training and prediction processes

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

    statistical data and samples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromnode
    -0.59
    awtextra
    -0.54
     AssemblyProduct
    -0.53
     betweenstory
    -0.49
    }{*}{
    -0.48
    Tembelea
    -0.48
    semibold
    -0.45
    WriteTagHelper
    -0.43
    SpringRunner
    -0.43
    fortawesome
    -0.43
    POSITIVE LOGITS
    Tracce
    0.45
    SOUNDBITE
    0.44
     Estuary
    0.43
     חיצוניים
    0.42
    âmica
    0.40
     incendie
    0.40
     Feuer
    0.39
     lievito
    0.38
    iNdEx
    0.38
     communautaire
    0.36
    Act Density 0.003%

    No Known Activations