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

    Neuronpedia

    INDEX
    Explanations

    temporal phrases indicating elapsed time

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

    Time references followed by "later" and "still"

    np_acts-logits-general · gemini-2.0-flash

    later followed by period of continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.63
    Soorten
    -0.59
    сама
    -0.57
    acuzzi
    -0.56
    NSNumber
    -0.53
     لمدة
    -0.52
    gdala
    -0.52
    indakan
    -0.51
    一辈子
    -0.51
    hability
    -0.50
    POSITIVE LOGITS
     still
    0.83
    still
    0.83
     Still
    0.78
    Still
    0.77
     STILL
    0.70
    Према
    0.65
     fortfarande
    0.63
     fortsatt
    0.59
    webElementXpaths
    0.59
     scolas
    0.58
    Act Density 0.152%

    No Known Activations