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

    Neuronpedia

    INDEX
    Explanations

    directories

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of directories, listings, guides, and similar catalog‐style headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     확
    -0.07
    .init
    -0.07
     winding
    -0.07
    訂
    -0.07
    ỹ
    -0.06
     elemento
    -0.06
    CppCodeGen
    -0.06
     measuring
    -0.06
    ugador
    -0.06
    olland
    -0.06
    POSITIVE LOGITS
     atlas
    0.08
     Atlas
    0.07
     Directory
    0.07
    leen
    0.07
    ві
    0.06
     nervous
    0.06
    нуться
    0.06
    जर
    0.06
    .forEach
    0.06
     Registry
    0.06
    Act Density 0.008%

    No Known Activations