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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron activates on the names (initials and surname) of judges—e.g. “Richard S. Arnold”—in the opinion headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Threshold
    -0.06
     Hait
    -0.06
     plastics
    -0.06
     Tamb
    -0.06
     группы
    -0.06
     kì
    -0.06
     toute
    -0.06
     fila
    -0.06
    eteria
    -0.06
     Archbishop
    -0.06
    POSITIVE LOGITS
    .Fill
    0.07
    createQueryBuilder
    0.07
    Std
    0.06
     weekends
    0.06
    balances
    0.06
     Especially
    0.06
    ifié
    0.06
    �
    0.06
     mutating
    0.06
     lifestyles
    0.06
    Act Density 0.013%

    No Known Activations