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

    Neuronpedia

    INDEX
    Explanations

    references to time-related metrics such as age, duration, and intervals

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

    Time durations

    np_acts-logits-general · gemini-2.0-flash

    time or distance measures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    but
    -0.34
    But
    -0.32
     But
    -0.30
    as
    -0.30
     ratusan
    -0.29
     Farbe
    -0.29
    meaning
    -0.29
     ribuan
    -0.28
     thousands
    -0.28
     for
    -0.28
    POSITIVE LOGITS
    ſelf
    0.87
     queſta
    0.85
     ſche
    0.83
    AddTagHelper
    0.82
    enderror
    0.80
     verſch
    0.79
     MainAxisSize
    0.77
    niſſe
    0.75
    <pad>
    0.74
    ſelves
    0.74
    Act Density 0.317%

    No Known Activations