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

    Neuronpedia

    INDEX
    Explanations

    time and temporal context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    1.09
    いる
    0.92
    ร์
    0.92
    ات
    0.90
     bathrobe
    0.89
    sla
    0.89
    ים
    0.89
    𝘴
    0.87
    ս
    0.87
     veuillez
    0.86
    POSITIVE LOGITS
     peacetime
    0.83
    واخر
    0.82
     sized
    0.80
    end
    0.79
     adept
    0.77
    otrexate
    0.71
    autocomplete
    0.71
     Shipbuilding
    0.71
    вна
    0.70
    Ҫ
    0.70
    Act Density 0.089%

    No Known Activations