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

    Neuronpedia

    INDEX
    Explanations

    periods and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    最近
    0.48
     when
    0.46
     начина
    0.46
    早在
    0.46
     quando
    0.45
    現在は
    0.45
    앉
    0.45
    when
    0.45
     ভবিষ্যতে
    0.44
     όταν
    0.43
    POSITIVE LOGITS
     gradually
    0.57
    不断
    0.54
     steadily
    0.54
     intermittently
    0.54
     various
    0.53
     Gradually
    0.51
     कई
    0.51
     develops
    0.51
     பல்வேறு
    0.50
    様々な
    0.50
    Act Density 0.163%

    No Known Activations