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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting numeric tokens—especially decimal numbers or numbered section headings—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uml
    -0.07
    JECT
    -0.07
     motivate
    -0.06
    .helpers
    -0.06
     Grave
    -0.06
    ậ
    -0.06
     deviation
    -0.06
     attract
    -0.06
    KeyListener
    -0.06
    LinearLayout
    -0.06
    POSITIVE LOGITS
     sizi
    0.07
    $array
    0.06
    ='".$
    0.06
     oferta
    0.06
     surrender
    0.06
    }}{{
    0.06
    reak
    0.06
     domestically
    0.06
    annonce
    0.06
    .setInt
    0.06
    Act Density 0.002%

    No Known Activations