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

    Neuronpedia

    INDEX
    Explanations

    reference

    np_max-act · gemini-2.0-flash

    This neuron detects legal‐style cross‐references to other documents (e.g. “incorporated … by reference”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information related to medical imaging technologies and their applications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lunches
    -0.07
     stagnant
    -0.06
     granny
    -0.06
    妻
    -0.06
     wrink
    -0.06
    άνα
    -0.06
     نیرو
    -0.06
     в
    -0.06
    006
    -0.06
     loung
    -0.06
    POSITIVE LOGITS
    Miss
    0.08
     exponentially
    0.06
    meter
    0.06
     LOCK
    0.06
     Miss
    0.06
    	user
    0.06
    _lists
    0.06
    }))↵↵
    0.06
     previously
    0.06
    tréal
    0.06
    Act Density 0.001%

    No Known Activations