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

    Neuronpedia

    INDEX
    Explanations

    Debian server

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     پذیر
    0.42
    珽
    0.40
     pubblic
    0.40
     Tính
    0.39
     Хоро
    0.39
     lấy
    0.38
    publique
    0.38
     giggle
    0.38
     Audience
    0.38
    थिंग
    0.38
    POSITIVE LOGITS
     случаи
    0.45
     Krueger
    0.41
     долла
    0.40
     результата
    0.40
    瞰
    0.39
    maxWidth
    0.39
     случаев
    0.39
    ومان
    0.39
    sley
    0.38
     компонентов
    0.38
    Act Density 0.000%

    No Known Activations