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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron detects Vulkan‐API identifiers and macros (tokens like “VK”, “Vk…” and “Vulkan” headers).

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

    elements related to authentication and security protocols.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ----↵
    -0.07
    ildo
    -0.07
    iktig
    -0.07
     WARRANTY
    -0.07
    Batman
    -0.07
    busy
    -0.06
    겨
    -0.06
    าน
    -0.06
    (Texture
    -0.06
    ุด
    -0.06
    POSITIVE LOGITS
     üzerinde
    0.08
     lent
    0.06
    .Age
    0.06
     Having
    0.06
    Bur
    0.06
     demasi
    0.06
     giới
    0.06
     ülk
    0.06
    NSNotificationCenter
    0.06
     Bur
    0.06
    Act Density 0.022%

    No Known Activations