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

    Neuronpedia

    INDEX
    Explanations

    pattern following specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    time
    0.73
     time
    0.59
    Time
    0.52
     Time
    0.50
    ogr
    0.44
    ǔ
    0.42
    TIME
    0.42
    的時間
    0.41
    bit
    0.40
    cer
    0.40
    POSITIVE LOGITS
    跇
    0.45
    自动化
    0.43
     automating
    0.41
     tableView
    0.40
     સામ
    0.39
    வ்வேறு
    0.39
    亼
    0.39
     Automat
    0.39
    扌
    0.38
    豺
    0.38
    Act Density 0.000%

    No Known Activations