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

    Neuronpedia

    INDEX
    Explanations

    generated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maupun
    0.55
     zowel
    0.55
     因为
    0.51
     ataupun
    0.50
    比如说
    0.49
     nejen
    0.49
    New
    0.49
     zarówno
    0.48
    INCLUDING
    0.46
     özellikle
    0.45
    POSITIVE LOGITS
    이고
    0.64
     nên
    0.58
     and
    0.55
     struggling
    0.54
    しかも
    0.54
     attempting
    0.52
     joten
    0.52
    而且
    0.52
    なので
    0.52
     말투
    0.49
    Act Density 0.002%

    No Known Activations