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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash

    The neuron fires on Python return statements—especially the base‐case `return []` lines in recursive code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    Python code for sorting algorithms.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _auto
    -0.07
    -effects
    -0.07
     WebSocket
    -0.07
    .annotation
    -0.07
    "One
    -0.07
     Islands
    -0.07
    analyze
    -0.07
     frosting
    -0.06
     Managed
    -0.06
    ennis
    -0.06
    POSITIVE LOGITS
    ¦
    0.06
     Celebr
    0.06
     ภาษ
    0.06
     Jub
    0.06
     cuatro
    0.06
     вій
    0.06
    .Categories
    0.06
     meters
    0.06
     Px
    0.06
    ezpeč
    0.05
    Act Density 0.014%

    No Known Activations