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

    Neuronpedia

    INDEX
    Explanations

    union

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find numeric literals in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    RITE
    -0.08
    PUR
    -0.08
     stair
    -0.07
    voucher
    -0.06
    pcodes
    -0.06
     Bon
    -0.06
    artifact
    -0.06
     Close
    -0.06
     viscosity
    -0.06
     Window
    -0.06
    POSITIVE LOGITS
     originated
    0.07
    alias
    0.07
     unnamed
    0.07
     threading
    0.06
    ुल
    0.06
     берег
    0.06
    _queue
    0.06
     Union
    0.06
     shareholder
    0.06
     according
    0.06
    Act Density 0.001%

    No Known Activations