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 selectively activates on numeric tokens—especially decimal numbers—used in patent citations or similar numeric references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	JSONObject
    -0.07
     supplies
    -0.06
    (IM
    -0.06
    primir
    -0.06
    (selected
    -0.06
     '%
    -0.06
     Nhưng
    -0.06
     ______
    -0.06
    Conversation
    -0.06
    (parameters
    -0.06
    POSITIVE LOGITS
    uation
    0.06
     度
    0.06
     peacefully
    0.06
    Model
    0.06
    ipher
    0.06
     gymn
    0.06
    ushi
    0.06
    ्टर
    0.06
    uma
    0.06
    pies
    0.06
    Act Density 0.001%

    No Known Activations