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

    Neuronpedia

    INDEX
    Explanations

    code manipulating tree nodes

    np_max-act · gemini-2.0-flash

    The neuron activates primarily on numeric literals (numbers and decimal values) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Wolf
    -0.06
     antioxid
    -0.06
     sessiz
    -0.06
    وغ
    -0.06
    骨
    -0.06
    ニニ
    -0.06
     hiçbir
    -0.06
     Naomi
    -0.06
    ढ
    -0.06
     prelim
    -0.06
    POSITIVE LOGITS
    ỗng
    0.07
    adopt
    0.07
    flate
    0.07
     "",↵
    0.06
     DIRECTORY
    0.06
    "}},↵
    0.06
    Implemented
    0.06
    Table
    0.06
     prostoru
    0.06
    	mod
    0.06
    Act Density 0.006%

    No Known Activations