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

    Neuronpedia

    INDEX
    Explanations

    specific measurements of time, age, or quantity

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

    "year" or "years" followed by an age

    np_acts-logits-general · gemini-2.0-flash

    year old ages and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thousands
    -0.94
     hundreds
    -0.88
     Thousands
    -0.82
     millions
    -0.81
     milhares
    -0.79
     billions
    -0.79
    thousands
    -0.74
     cientos
    -0.74
     ratusan
    -0.72
     Hundreds
    -0.70
    POSITIVE LOGITS
    /$
    0.66
    짜
    0.61
    RunAsync
    0.61
     olds
    0.60
     itch
    0.60
     affair
    0.56
     rule
    0.55
    +
    0.55
    -${
    0.55
    $+
    0.54
    Act Density 0.254%

    No Known Activations