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

    Neuronpedia

    INDEX
    Explanations

    Name

    np_max-act · gemini-2.0-flash

    This neuron activates on XAML attribute names, in particular the “Name=” attribute on XML elements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lux
    -0.07
    ]^
    -0.06
     BASIC
    -0.06
    (fun
    -0.06
    603
    -0.06
    bk
    -0.06
    arious
    -0.06
    ]-
    -0.06
     ($
    -0.06
    以来
    -0.06
    POSITIVE LOGITS
    remaining
    0.07
    _constants
    0.07
     رنگ
    0.06
    ают
    0.06
     Suff
    0.06
    TextLabel
    0.06
     Swal
    0.06
     Cornwall
    0.06
     directional
    0.06
     پس
    0.06
    Act Density 0.001%

    No Known Activations