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

    Neuronpedia

    INDEX
    Explanations

    stars and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    新宿
    0.41
     рождения
    0.41
     Вели
    0.41
    Xx
    0.40
     bắn
    0.40
     विकिरण
    0.39
     शिप
    0.39
    音乐
    0.39
     দীপ
    0.38
     Один
    0.38
    POSITIVE LOGITS
     obiekt
    0.42
     planets
    0.40
     dajj
    0.39
    क्टी
    0.39
     objetos
    0.38
    retry
    0.38
     тог
    0.38
     arre
    0.38
     objects
    0.37
    umbent
    0.37
    Act Density 0.023%

    No Known Activations