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

    Neuronpedia

    INDEX
    Explanations

    for example instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sân
    0.41
     букмекерлик
    0.41
    덬
    0.40
    რა
    0.39
     reçu
    0.38
    énom
    0.38
    тка
    0.37
    景象
    0.36
     hiển
    0.36
    wohl
    0.36
    POSITIVE LOGITS
     सूचीबद्ध
    0.39
     শতকরা
    0.38
     Exploration
    0.37
     Listed
    0.37
     Explorer
    0.37
     Kinney
    0.36
     Exploring
    0.36
     Trink
    0.35
     Find
    0.35
    章节
    0.35
    Act Density 0.000%

    No Known Activations