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

    Neuronpedia

    INDEX
    Explanations

    cost, scalability, safety, visual,evolving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ٨
    0.55
     Михаил
    0.52
     Наталья
    0.52
     Фурга
    0.51
    深化
    0.50
     kautta
    0.50
    Berikut
    0.48
     Тогда
    0.48
     vervolgens
    0.48
     pertama
    0.46
    POSITIVE LOGITS
    amen
    0.42
     מש
    0.41
    item
    0.40
    ak
    0.40
     schützen
    0.40
    br
    0.39
    im
    0.38
     residence
    0.38
    en
    0.38
     ail
    0.38
    Act Density 0.002%

    No Known Activations