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

    Neuronpedia

    INDEX
    Explanations

    ML support and frequent patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িবদ্ধ
    0.44
    Plugins
    0.43
    插件
    0.40
     образа
    0.39
    LocalStorage
    0.39
    妫
    0.39
    उथ
    0.38
    attha
    0.38
    Transicao
    0.38
    REETYPE
    0.38
    POSITIVE LOGITS
     support
    0.39
     Leather
    0.39
     base
    0.39
     trust
    0.38
     leather
    0.38
     condos
    0.38
    requent
    0.37
     ejército
    0.37
     حمایت
    0.37
     Alcat
    0.37
    Act Density 0.002%

    No Known Activations