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

    Neuronpedia

    INDEX
    Explanations

    package reference

    np_max-act · gemini-2.0-flash

    The neuron detects XML markup for package declarations (e.g. `<package>` tags and `<PackageReference>` elements) in project or packages config files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Chen
    -0.07
    だろう
    -0.07
    ÓN
    -0.06
     MatTable
    -0.06
    ниця
    -0.06
    OND
    -0.06
    เสนอ
    -0.06
     redundancy
    -0.06
    екс
    -0.06
     Nimbus
    -0.06
    POSITIVE LOGITS
     grade
    0.07
    Flush
    0.06
    lux
    0.06
    ────
    0.06
     přisp
    0.06
    의
    0.06
    音乐
    0.06
    .pc
    0.06
     للإ
    0.06
     ketogenic
    0.06
    Act Density 0.001%

    No Known Activations