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

    Neuronpedia

    INDEX
    Explanations

    time and deadlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     máxim
    0.41
     يصل
    0.41
     eventually
    0.40
     যখন
    0.39
     último
    0.39
     discounts
    0.39
    max
    0.38
     máximo
    0.38
     última
    0.38
    最大
    0.36
    POSITIVE LOGITS
    Until
    0.69
     Until
    0.61
     এখন
    0.60
     nyní
    0.60
    现在
    0.59
     until
    0.57
     сейчас
    0.57
    until
    0.57
     ahora
    0.56
     now
    0.55
    Act Density 0.019%

    No Known Activations