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

    Neuronpedia

    INDEX
    Explanations

    police

    np_max-act · gemini-2.0-flash

    The neuron detects terms related to official investigations or law‐enforcement authorities (e.g. investigation, police, authorities).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .quest
    -0.07
     Farms
    -0.07
    111
    -0.06
     alloy
    -0.06
    рю
    -0.06
    Cómo
    -0.06
     نظام
    -0.06
    aramel
    -0.06
     familiarity
    -0.06
    ("/")↵
    -0.06
    POSITIVE LOGITS
     погод
    0.07
    تبه
    0.07
     pose
    0.07
     MOT
    0.06
     initialization
    0.06
     sax
    0.06
    881
    0.06
    :');↵
    0.06
     socket
    0.06
    ]++;↵
    0.06
    Act Density 0.011%

    No Known Activations