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

    Neuronpedia

    INDEX
    Explanations

    current or present state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    最初は
    0.54
     ইতিমধ্যে
    0.54
     nantinya
    0.53
    на
    0.53
     később
    0.53
     இதுவரை
    0.52
     pierwsze
    0.52
     ابتدا
    0.50
     později
    0.49
     successivamente
    0.49
    POSITIVE LOGITS
    adays
    0.94
    varande
    0.90
     Grâce
    0.75
    t
    0.71
    spapers
    0.69
     defunct
    0.64
     happily
    0.64
    tım
    0.63
    tembre
    0.62
    comers
    0.62
    Act Density 0.677%

    No Known Activations