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

    Neuronpedia

    INDEX
    Explanations

    quantitative data related to accommodation capacity in various settings

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

    Numbers in the tens

    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
     millions
    -0.85
     two
    -0.80
     Millions
    -0.75
     billions
    -0.74
    Two
    -0.71
    two
    -0.71
     Two
    -0.70
    millions
    -0.69
     jutaan
    -0.69
     TWO
    -0.67
    POSITIVE LOGITS
     dozen
    1.35
     thirty
    1.31
     twenty
    1.30
     forty
    1.27
     fifty
    1.22
     sixty
    1.21
    Twenty
    1.20
    Thirty
    1.19
     Thirty
    1.17
    Forty
    1.15
    Act Density 0.441%

    No Known Activations