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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating large quantities or populations

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

    numbers in the thousands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ][
    -0.41
     durumu
    -0.35
    bf
    -0.34
     Arne
    -0.32
     πως
    -0.32
    dataclass
    -0.31
    vency
    -0.31
    VB
    -0.31
     débats
    -0.31
    BF
    -0.31
    POSITIVE LOGITS
     thousands
    1.86
    thousands
    1.79
    Thousands
    1.71
     Thousands
    1.69
     thousand
    1.60
     THOUS
    1.52
    thousand
    1.42
     hundreds
    1.42
     Thousand
    1.41
     millions
    1.40
    Act Density 0.004%

    No Known Activations