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

    Neuronpedia

    INDEX
    Explanations

    title="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    м
    0.97
    німа
    0.97
     acides
    0.97
     CLIENTI
    0.94
     souha
    0.92
    maları
    0.89
     dacă
    0.89
     acide
    0.89
     réellement
    0.89
    𝐼
    0.88
    POSITIVE LOGITS
    place
    1.05
     Name
    0.95
     जिसे
    0.92
    utors
    0.91
    berg
    0.91
    name
    0.87
     einer
    0.86
    age
    0.86
     Maßnahmen
    0.86
    бы
    0.84
    Act Density 0.001%

    No Known Activations