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

    Neuronpedia

    INDEX
    Explanations

    Task

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of “Task” (especially in NSURLSession dataTask…WithRequest calls), i.e. tokens that name or start off an asynchronous network‐request task.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     přičemž
    -0.07
     SWAT
    -0.07
    ený
    -0.07
    leriyle
    -0.07
    _traits
    -0.06
    "nil
    -0.06
     refurbished
    -0.06
     angrily
    -0.06
     Kürt
    -0.06
    英雄
    -0.06
    POSITIVE LOGITS
     αγ
    0.07
    ¿Â
    0.07
    نم
    0.07
     HS
    0.06
    โพ
    0.06
    quires
    0.06
     alkal
    0.06
    ाहत
    0.06
     реак
    0.06
    การแข
    0.06
    Act Density 0.000%

    No Known Activations