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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and periods

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

    address components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.99
     faſt
    -0.81
     tranſ
    -0.73
    ########.
    -0.71
     Biôgrafia
    -0.71
    uxxxx
    -0.69
     виправивши
    -0.69
     queſta
    -0.67
    TypedDataSet
    -0.67
     EconPapers
    -0.67
    POSITIVE LOGITS
    ,
    0.47
     ,
    0.41
     are
    0.36
    houden
    0.35
     will
    0.34
    .
    0.34
     a
    0.34
     initially
    0.33
     place
    0.33
     Connectez
    0.33
    Act Density 0.109%

    No Known Activations