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

    Neuronpedia

    INDEX
    Explanations

    rails, mix, and database migrations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Modules
    0.41
     render
    0.38
     collection
    0.38
     marginRight
    0.37
     modules
    0.36
     collections
    0.36
     পারে
    0.36
     equity
    0.36
     alien
    0.36
     Strait
    0.36
    POSITIVE LOGITS
     TASK
    0.43
     задачи
    0.43
    TaskManager
    0.43
    任务
    0.43
    task
    0.39
    GAN
    0.39
    躁
    0.38
    Task
    0.38
    気が
    0.38
    பாத
    0.38
    Act Density 0.003%

    No Known Activations