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

    Neuronpedia

    INDEX
    Explanations

    of [city/company name]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ant
    0.73
    alte
    0.64
    el
    0.61
    様子
    0.60
    έ
    0.60
    and
    0.59
    ed
    0.57
    enium
    0.56
    ithe
    0.56
    elsk
    0.55
    POSITIVE LOGITS
     kelamin
    0.71
     الد
    0.62
     осуществля
    0.61
    نا
    0.59
     Да
    0.59
     reckons
    0.59
     контроля
    0.59
     Фа
    0.57
     비롯
    0.57
     refills
    0.56
    Act Density 0.401%

    No Known Activations