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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    references to legal institutions and their historical context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron primarily detects numeric expressions such as years, section numbers, and other numerical citations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Том
    -0.07
     Command
    -0.07
    aes
    -0.06
     Patterns
    -0.06
     sobie
    -0.06
     Oil
    -0.06
     dieses
    -0.06
     cmds
    -0.06
     hab
    -0.06
    ifton
    -0.06
    POSITIVE LOGITS
    {{{
    0.06
    Communic
    0.06
     bì
    0.06
     disproportionate
    0.06
    0.06
    °N
    0.06
    embourg
    0.06
     decorators
    0.06
    0.06
    更
    0.06
    Act Density 0.158%

    No Known Activations