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

    Neuronpedia

    INDEX
    Explanations

    upcoming events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    γρα
    0.41
    บ
    0.39
     bruke
    0.39
     Initially
    0.39
    fabric
    0.38
    उस
    0.38
    μί
    0.38
    दरअसल
    0.38
    采
    0.38
    დეს
    0.37
    POSITIVE LOGITS
     upcoming
    0.96
    即将
    0.95
     sedang
    0.83
     imminent
    0.80
     recently
    0.79
     soon
    0.79
    upcoming
    0.77
     sắp
    0.77
     đang
    0.76
     nearing
    0.76
    Act Density 0.024%

    No Known Activations