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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on XML/serialization attribute annotations (e.g. XmlRoot, XmlElement, Serializable) applied to classes or fields.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     waypoint
    -0.08
    idenav
    -0.07
     survival
    -0.07
    camatan
    -0.07
    _REDIRECT
    -0.07
    qe
    -0.07
    ousedown
    -0.06
    .Bounds
    -0.06
     Registrar
    -0.06
     shepherd
    -0.06
    POSITIVE LOGITS
     URLSession
    0.07
    pově
    0.06
    )]↵
    0.06
     менше
    0.06
     aa
    0.06
     ako
    0.06
     america
    0.06
    ])↵
    0.06
     boto
    0.06
     tylko
    0.06
    Act Density 0.013%

    No Known Activations