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

    Neuronpedia

    INDEX
    Explanations

    quantities and comparative metrics related to industry and business

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

    Numbers followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     passaggio
    -0.53
    acamole
    -0.50
    verwaltung
    -0.50
     foglie
    -0.49
    ليب
    -0.49
     mauvaises
    -0.49
     graines
    -0.48
    ัตร
    -0.47
     agricoles
    -0.47
     asmen
    -0.47
    POSITIVE LOGITS
     thousand
    0.86
     million
    0.80
     hundred
    0.75
     AssemblyCompany
    0.75
     dozen
    0.69
    thousand
    0.68
    hundred
    0.68
     thousands
    0.68
    httphttps
    0.67
    tens
    0.65
    Act Density 0.278%

    No Known Activations