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

    Neuronpedia

    INDEX
    Explanations

    security

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of security or protective personnel and measures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     외국
    -0.07
    义
    -0.06
     artisan
    -0.06
     yaygın
    -0.06
     pz
    -0.06
     نرم
    -0.06
    увався
    -0.06
    	glBind
    -0.06
    ún
    -0.06
     Toyota
    -0.06
    POSITIVE LOGITS
    nav
    0.07
     SECURITY
    0.07
     narcotics
    0.07
     security
    0.06
    ?'
    0.06
     Ashley
    0.06
    csi
    0.06
     shrink
    0.06
    体育
    0.06
    <Comment
    0.06
    Act Density 0.028%

    No Known Activations