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

    Neuronpedia

    INDEX
    Explanations

    Code syntax

    np_max-act · gemini-2.0-flash

    This neuron activates on code patterns that access or query properties/fields—particularly JSON or object property lookups and calls like `.contains`, `.size`, or fetching values via keys.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Буд
    -0.08
    销售
    -0.07
    маз
    -0.07
    _study
    -0.07
    缺
    -0.06
    Hundreds
    -0.06
    Road
    -0.06
    (play
    -0.06
    <List
    -0.06
     persecution
    -0.06
    POSITIVE LOGITS
     FT
    0.06
     porcelain
    0.06
     sagt
    0.06
     Freeman
    0.06
    들의
    0.06
     норм
    0.06
    otoxic
    0.06
    ournemouth
    0.06
    etest
    0.06
    TEGER
    0.06
    Act Density 0.013%

    No Known Activations