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 numeric tokens—especially sequences of digits and decimal numbers such as those used for docket/case or citation numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    legal terminology and concepts related to court cases and appeals.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -neutral
    -0.08
     webs
    -0.07
    MinMax
    -0.07
    TERNAL
    -0.07
     Employees
    -0.07
    .levels
    -0.06
    Bei
    -0.06
     entreg
    -0.06
    .iter
    -0.06
    .expected
    -0.06
    POSITIVE LOGITS
    _SDK
    0.06
    abo
    0.06
    픽
    0.06
    ламент
    0.06
    (store
    0.05
    quite
    0.05
     pitch
    0.05
    (distance
    0.05
     coral
    0.05
    LOUD
    0.05
    Act Density 0.003%

    No Known Activations