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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases, particularly those indicating speed and efficiency in processes

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

    Time duration/interval

    np_acts-logits-general · gemini-2.0-flash

    measures of short duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     towards
    -0.53
     CURIAM
    -0.53
    出版年
    -0.48
    aysia
    -0.47
    lastIndexOf
    -0.47
    SceneManagement
    -0.47
    skjaer
    -0.46
    )$/,
    -0.46
     Towards
    -0.45
    endphp
    -0.45
    POSITIVE LOGITS
     løpet
    0.64
     fastest
    0.64
     quickly
    0.62
    astify
    0.62
     cepat
    0.61
    knię
    0.61
    短短
    0.58
    ValueStyle
    0.58
     препратки
    0.58
     بسر
    0.57
    Act Density 0.153%

    No Known Activations