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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    This neuron detects SQL aggregation operations (e.g. SUM, MAX, AVG) and their associated aliasing (the AS keyword).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    [cell
    -0.07
    	token
    -0.07
     Kazakhstan
    -0.06
     Něk
    -0.06
    έργ
    -0.06
     Belarus
    -0.06
     Miller
    -0.06
    えて
    -0.06
    377
    -0.06
    232
    -0.06
    POSITIVE LOGITS
    افق
    0.07
    arshal
    0.06
    	ASSERT
    0.06
     replicas
    0.06
    ISO
    0.06
    �
    0.06
    ?")↵
    0.06
    sto
    0.06
    είου
    0.06
    onto
    0.06
    Act Density 0.004%

    No Known Activations