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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    This neuron activates on floating‐point numeric literals (decimal constants) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    奖
    -0.08
    .related
    -0.06
    ughty
    -0.06
    _tickets
    -0.06
    \Web
    -0.06
     sculpt
    -0.06
     Carson
    -0.06
    :↵↵↵↵↵↵
    -0.06
    ccess
    -0.05
     diapers
    -0.05
    POSITIVE LOGITS
     işlem
    0.07
    Oi
    0.07
     oss
    0.07
     PCA
    0.07
    Wide
    0.06
    �
    0.06
    +='
    0.06
     minimum
    0.06
    ImageRelation
    0.06
     irre
    0.06
    Act Density 0.003%

    No Known Activations