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

    Neuronpedia

    INDEX
    Explanations

    terms related to innovation and progress in technology

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

    positive suffixes followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dalamnya
    -0.60
     виправивши
    -0.60
    alcool
    -0.54
    ambién
    -0.53
     siglos
    -0.52
     Wikiseite
    -0.52
     siitä
    -0.50
    Бахар
    -0.50
     décadas
    -0.50
     sitä
    -0.49
    POSITIVE LOGITS
     private
    0.56
     accurate
    0.54
     great
    0.50
     unusual
    0.50
     original
    0.49
     oral
    0.49
     additional
    0.48
     informal
    0.48
     verbal
    0.48
    小さな
    0.47
    Act Density 5.382%

    No Known Activations