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

    Neuronpedia

    INDEX
    Explanations

    Access and authorization

    np_max-act · gemini-2.0-flash

    The neuron activates on sequences of digits and legal citation patterns (e.g. case numbers, statute sections, years).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    範
    -0.06
    >,
    -0.06
    yaml
    -0.06
    기는
    -0.06
    .hm
    -0.06
    ervers
    -0.06
     examinations
    -0.06
     premiums
    -0.06
    emsp
    -0.06
    یری
    -0.06
    POSITIVE LOGITS
     Diabetes
    0.07
    .chart
    0.07
    setCurrent
    0.07
    .Append
    0.07
    ########################################
    0.07
    ################################
    0.06
    Opaque
    0.06
     letra
    0.06
     свет
    0.06
    .loss
    0.06
    Act Density 0.060%

    No Known Activations