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

    Neuronpedia

    INDEX
    Explanations

    chemical products

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of reaction outcomes—words like “product,” “products,” “metabolite,” or “metabolites.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ήλ
    -0.07
     KP
    -0.07
    _bs
    -0.06
     kidn
    -0.06
     Diseases
    -0.06
    	        ↵
    -0.06
    _lower
    -0.06
    resa
    -0.06
    models
    -0.06
    	day
    -0.06
    POSITIVE LOGITS
    .oauth
    0.06
     overlay
    0.06
     Attend
    0.06
    แฟ
    0.06
     üretim
    0.06
     �
    0.06
     بنابراین
    0.06
    crew
    0.06
     flexGrow
    0.06
     şeklinde
    0.06
    Act Density 0.031%

    No Known Activations