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

    Neuronpedia

    INDEX
    Explanations

    mathematics, large numbers, infinity

    np_max-act · gemini-2.0-flash

    This neuron detects numerical quantities, especially floating‐point or approximate numeric expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     نفت
    -0.07
     Nixon
    -0.07
    of
    -0.07
    _dataset
    -0.07
    ontrol
    -0.07
    OMBRE
    -0.06
    idal
    -0.06
    _epi
    -0.06
    rys
    -0.06
     HashMap
    -0.06
    POSITIVE LOGITS
    Replacement
    0.08
     expr
    0.07
    mitt
    0.06
     �
    0.06
    逸
    0.06
     exh
    0.06
    ussy
    0.06
    星
    0.06
    TestId
    0.06
    허
    0.06
    Act Density 0.007%

    No Known Activations