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

    Neuronpedia

    INDEX
    Explanations

    pray

    np_max-act · gemini-2.0-flash

    This neuron activates on the substring “rospray,” i.e. it detects mentions of electrospray (ionization).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    conds
    -0.06
    Merchant
    -0.06
    ynec
    -0.06
    	curr
    -0.06
    channel
    -0.06
     contradiction
    -0.06
    useum
    -0.06
     objections
    -0.06
     loin
    -0.06
    τρι
    -0.06
    POSITIVE LOGITS
     Carnival
    0.07
     Honestly
    0.06
    .Raw
    0.06
     hash
    0.06
     europé
    0.06
    **)
    0.06
     polyline
    0.06
     Shape
    0.06
     Graphics
    0.06
     getir
    0.06
    Act Density 0.001%

    No Known Activations