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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptors and numbers associated with amounts or measurements

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

    Numbers followed by units of time

    np_acts-logits-general · gemini-2.0-flash

    number followed by years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LabelTagHelper
    -0.67
     transférez
    -0.61
    GEBURTSDATUM
    -0.58
     saites
    -0.57
     akár
    -0.57
    čeno
    -0.54
    umumkan
    -0.53
    angliski
    -0.53
     apă
    -0.53
    ποι
    -0.52
    POSITIVE LOGITS
     months
    0.79
     weeks
    0.75
     consecutive
    0.74
     different
    0.71
     dozen
    0.70
     successive
    0.66
     years
    0.65
     days
    0.62
    httphttps
    0.62
    dozen
    0.61
    Act Density 0.435%

    No Known Activations