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

    Neuronpedia

    INDEX
    Explanations

    numerical data relating to quantities and statistics

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

    Numbers modified with "of", "than", or a comma

    np_acts-logits-general · gemini-2.0-flash

    numerical quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.57
     }{@
    -0.51
    httphttps
    -0.49
     @"/
    -0.46
     تكبرها
    -0.46
    ///</
    -0.46
     ویکی‌پدی
    -0.45
    ngdoc
    -0.42
     snippetHide
    -0.41
     AssemblyCulture
    -0.40
    POSITIVE LOGITS
     thousands
    0.82
     hundreds
    0.78
     dozens
    0.75
    undred
    0.70
     dozen
    0.68
     tens
    0.68
     many
    0.67
    thousands
    0.67
     numerous
    0.66
    hundreds
    0.63
    Act Density 0.255%

    No Known Activations