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

    Neuronpedia

    INDEX
    Explanations

    VPNs, shark, pad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нические
    0.90
    ﻥ
    0.89
     सिलेक्शन
    0.89
    шению
    0.88
    чным
    0.88
    баты
    0.86
    тным
    0.85
    INavigation
    0.84
    чных
    0.84
     йөк
    0.84
    POSITIVE LOGITS
    Лі
    0.98
     істо
    0.96
     miglia
    0.93
    Пре
    0.89
     autorità
    0.88
     année
    0.88
     ragazzi
    0.88
    </sup>
    0.85
    ly
    0.84
     êtes
    0.84
    Act Density 0.001%

    No Known Activations