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

    Neuronpedia

    INDEX
    Explanations

    custody

    np_max-act · gemini-2.0-flash

    The neuron detects references to a defendant’s custodial interrogation or statements made while in police custody.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tội
    -0.07
    iyeti
    -0.06
    eným
    -0.06
     puedes
    -0.06
     Wyn
    -0.06
    (out
    -0.06
     Trinity
    -0.06
    出去
    -0.06
    paration
    -0.06
    	string
    -0.06
    POSITIVE LOGITS
    -update
    0.07
    gtk
    0.07
     عاما
    0.06
    credit
    0.06
     Almanya
    0.06
     adventurer
    0.06
     complying
    0.06
    用品
    0.06
    การเล
    0.06
    Learn
    0.06
    Act Density 0.006%

    No Known Activations