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

    Neuronpedia

    INDEX
    Explanations

    debugging errors

    np_max-act · gemini-2.0-flash

    This neuron detects references to e-commerce “product” entities—especially product IDs and database-related mentions (e.g., “product ID,” “product database,” “Swell Commerce”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     heroine
    -0.07
     whore
    -0.07
    odies
    -0.07
     могла
    -0.06
    IEEE
    -0.06
    िकल
    -0.06
    kemiz
    -0.06
    018
    -0.06
    reate
    -0.06
    016
    -0.06
    POSITIVE LOGITS
    charAt
    0.07
     минут
    0.07
     investigator
    0.07
    That
    0.07
    .result
    0.07
    NSObject
    0.06
    .flatMap
    0.06
    Cont
    0.06
    ]=>
    0.06
    Fig
    0.06
    Act Density 0.074%

    No Known Activations