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

    Neuronpedia

    INDEX
    Explanations

    .Tasks

    np_max-act · gemini-2.0-flash

    The neuron fires on the C# “Task” keyword (i.e. async Task return types and the Task type in code).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ↵↵↵↵↵↵↵
    -0.07
    ede
    -0.07
    ↵↵↵↵↵↵↵↵↵
    -0.07
    ене
    -0.07
    iverz
    -0.06
    ymb
    -0.06
    RING
    -0.06
     Hyde
    -0.06
    _translation
    -0.06
     Cros
    -0.06
    POSITIVE LOGITS
    .Tasks
    0.10
     initialise
    0.07
     Estados
    0.07
     Fixes
    0.07
     έχει
    0.07
    Precision
    0.06
    _environment
    0.06
    entic
    0.06
     holidays
    0.06
     المل
    0.06
    Act Density 0.001%

    No Known Activations