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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron detects user queries asking for items “similar to” something—that is, prompts seeking recommendations by similarity.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unbelie
    -0.06
    	fp
    -0.06
     rever
    -0.06
     noen
    -0.06
    Nh
    -0.06
    iance
    -0.06
    	initial
    -0.06
    69
    -0.06
    lectual
    -0.06
    ocop
    -0.06
    POSITIVE LOGITS
    λι
    0.07
    TRAIN
    0.07
     Dün
    0.06
     '↵↵
    0.06
    /train
    0.06
    لية
    0.06
     RecyclerView
    0.06
     Connectivity
    0.06
    _AXIS
    0.06
    TableView
    0.06
    Act Density 0.016%

    No Known Activations