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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating completion or existing conditions

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

    Follows words like "so", "had", "is", "or"

    np_acts-logits-general · gemini-2.0-flash

    already / 已

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.72
     كومونز
    -0.70
     ISNI
    -0.59
     싶
    -0.54
    DataAnnotations
    -0.53
    Демографія
    -0.52
     NUKAT
    -0.52
     وصلة
    -0.52
    MLLoader
    -0.51
    Einzelnachweise
    -0.50
    POSITIVE LOGITS
     already
    4.57
    already
    4.12
     Already
    3.94
    Already
    3.81
     ALREADY
    3.52
     allerede
    2.97
     уже
    2.86
    ALREADY
    2.85
     redan
    2.84
     déjà
    2.84
    Act Density 0.832%

    No Known Activations