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

    Neuronpedia

    INDEX
    Explanations

    previous or past events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.74
    ב
    0.71
    ری
    0.69
    ش
    0.61
    ü
    0.59
     Ainda
    0.58
    ン
    0.58
     it
    0.55
    ال
    0.55
    के
    0.55
    POSITIVE LOGITS
    previous
    0.96
     previous
    0.89
    Previous
    0.87
    past
    0.80
     Previous
    0.79
     الماض
    0.76
     प्रीवियस
    0.74
     గత
    0.73
     предыду
    0.72
    过去的
    0.71
    Act Density 0.089%

    No Known Activations