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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially decimal or year numbers (often in parentheses) found in citations and reference entries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     occasional
    -0.07
     Davis
    -0.06
     sus
    -0.06
    ват
    -0.06
    Davis
    -0.06
     PA
    -0.06
    ">@
    -0.06
     nutritional
    -0.06
    Device
    -0.06
     Via
    -0.06
    POSITIVE LOGITS
    .MouseEventHandler
    0.07
    \(
    0.07
    Completion
    0.06
    린이
    0.06
     MAKE
    0.06
    .HeaderText
    0.06
    Git
    0.06
    .stack
    0.06
    otine
    0.06
     chill
    0.06
    Act Density 0.005%

    No Known Activations