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

    Neuronpedia

    INDEX
    Explanations

    crimes and convictions

    np_max-act · gemini-2.0-flash

    This neuron detects numeric legal references, such as statute and case citation numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    肩
    -0.08
     Wonder
    -0.07
     составе
    -0.06
     Арх
    -0.06
    YLeaf
    -0.06
     Griffin
    -0.06
     Wallet
    -0.06
     Blond
    -0.06
    (unique
    -0.06
     Journalism
    -0.06
    POSITIVE LOGITS
    -relative
    0.07
    -regexp
    0.07
    _oc
    0.06
    asionally
    0.06
     рекомендуется
    0.06
    öße
    0.06
    较
    0.06
    RYPTO
    0.06
     o
    0.06
    _ITEM
    0.06
    Act Density 0.010%

    No Known Activations