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

    Neuronpedia

    INDEX
    Explanations

    time periods or durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     લગભગ
    0.47
    ER
    0.47
    みたい
    0.47
    方向
    0.46
    拉
    0.46
    க்க
    0.45
    たくさん
    0.45
    q
    0.45
    =".
    0.45
    তান্ত্রিক
    0.45
    POSITIVE LOGITS
     decreed
    0.45
     кі
    0.44
     Connor
    0.43
     awards
    0.43
    finals
    0.42
     vows
    0.42
     salted
    0.42
     gages
    0.42
     Odds
    0.41
     fillets
    0.41
    Act Density 0.001%

    No Known Activations