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
    люб
    -0.06
     อ
    -0.06
     shade
    -0.06
     influx
    -0.06
    両
    -0.06
    cout
    -0.06
     inclu
    -0.06
    фров
    -0.06
    POSITIVE LOGITS
     task
    0.11
     Task
    0.09
    .Tasks
    0.08
    _TASK
    0.08
    (task
    0.08
     Tasks
    0.08
    Task
    0.08
    _tasks
    0.08
     tasks
    0.07
     tasked
    0.07
    Act Density 0.039%

    No Known Activations