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

    Neuronpedia

    INDEX
    Explanations

    task

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buildup
    -0.08
     swollen
    -0.07
    seo
    -0.07
     swelling
    -0.07
    photo
    -0.07
    ocy
    -0.07
     longevity
    -0.07
     POP
    -0.07
     climbers
    -0.06
    .UInt
    -0.06
    POSITIVE LOGITS
     task
    0.12
     tasks
    0.11
     Tasks
    0.09
     tasked
    0.08
    .Tasks
    0.08
     ta
    0.08
    task
    0.08
    _TASK
    0.07
    _tasks
    0.07
     Task
    0.07
    Act Density 0.039%

    No Known Activations