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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on XML or markup attributes labeling a code signature as C#, i.e. occurrences of the “C#” language marker in type/member signature entries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    meg
    -0.06
     adul
    -0.06
    _end
    -0.06
     Imaging
    -0.06
     dalle
    -0.06
    plemented
    -0.05
     Weaver
    -0.05
    break
    -0.05
    ụn
    -0.05
    -follow
    -0.05
    POSITIVE LOGITS
     indulge
    0.07
     Freddie
    0.07
    _OM
    0.07
     ',',
    0.07
    \Context
    0.06
     indul
    0.06
    .Metadata
    0.06
    (pdev
    0.06
     sofa
    0.06
     상담
    0.06
    Act Density 0.021%

    No Known Activations