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

    Neuronpedia

    INDEX
    Explanations

    functionality, knowledge, module, and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ма
    0.45
    伤害
    0.40
     o
    0.40
    ries
    0.40
    enf
    0.39
    ifornia
    0.39
    ibil
    0.38
    zeit
    0.38
    运行时
    0.38
    ze
    0.38
    POSITIVE LOGITS
     Extensions
    0.55
     Kode
    0.51
    ή
    0.50
     tenté
    0.49
     футболка
    0.49
    ($_
    0.48
    ríklad
    0.48
     ਰਹ
    0.47
     měl
    0.47
     داشت
    0.47
    Act Density 0.002%

    No Known Activations