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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash

    This neuron activates on XML (plist) markup tags, especially the `<key>…</key>`, `<string>`, `<array>`, and similar tag tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .).↵↵
    -0.07
    -unused
    -0.06
    stad
    -0.06
     devices
    -0.06
     ]).
    -0.06
     Pazar
    -0.06
    SID
    -0.06
    )).
    -0.06
    raně
    -0.06
     malaysia
    -0.06
    POSITIVE LOGITS
     armor
    0.06
     nominee
    0.06
     Prostitutas
    0.06
     documentation
    0.06
    шается
    0.06
     Loki
    0.06
     completionHandler
    0.06
     MouseEventArgs
    0.06
     CONTACT
    0.06
    valuator
    0.06
    Act Density 0.006%

    No Known Activations