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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    Java programming-related elements and structure.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron strongly activates on the key identifier tokens that appear as the final segments of package or module paths (e.g., the last name in an import or package declaration).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tutto
    -0.07
    Du
    -0.06
    리그
    -0.06
     FIN
    -0.06
    markdown
    -0.06
    idae
    -0.06
     soils
    -0.06
     tutte
    -0.06
     Welcome
    -0.06
    디
    -0.06
    POSITIVE LOGITS
     Loft
    0.07
    .GetObject
    0.06
    itian
    0.06
     －
    0.06
    _TYPE
    0.06
     Redistributions
    0.06
    _CID
    0.06
    pcs
    0.06
    ĩa
    0.06
    37
    0.06
    Act Density 0.005%

    No Known Activations