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

    Neuronpedia

    INDEX
    Explanations

    opening brackets

    np_max-act · gemini-2.0-flash

    This neuron detects the JSON “children” property that marks nested subtrees in the data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ünst
    -0.07
    Tau
    -0.07
     sudah
    -0.07
    τού
    -0.07
     readme
    -0.06
     params
    -0.06
     дод
    -0.06
    >';
↵
    -0.06
     viewport
    -0.06
     เด
    -0.06
    POSITIVE LOGITS
    _DDR
    0.07
    =NULL
    0.07
     PSU
    0.06
    σι
    0.06
    -M
    0.06
    кими
    0.06
    Catch
    0.06
    GLE
    0.06
    {}\
    0.06
    魂
    0.06
    Act Density 0.013%

    No Known Activations