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

    Neuronpedia

    INDEX
    Explanations

    pattern ; starting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lain
    0.46
     consecuencias
    0.45
     egiten
    0.45
     gives
    0.44
     同じ
    0.44
     provide
    0.44
     only
    0.44
     urgently
    0.44
     inconsc
    0.43
     geçen
    0.43
    POSITIVE LOGITS
     东
    0.47
    辐
    0.45
     تقريبا
    0.44
    东京
    0.44
    MutableArray
    0.43
    协会
    0.43
     ибо
    0.42
    uuuu
    0.41
    比特币
    0.41
    页面
    0.41
    Act Density 0.012%

    No Known Activations