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 detects XML attribute-name tokens (e.g. the “android:name” and similar attribute identifiers) in Android manifest–and related XML–files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _PKT
    -0.07
     analyzer
    -0.06
     oxygen
    -0.06
     Nd
    -0.06
     homophobic
    -0.06
     backstage
    -0.06
     Programm
    -0.06
     Na
    -0.06
    IND
    -0.06
    écial
    -0.06
    POSITIVE LOGITS
    ністю
    0.07
    θηκε
    0.07
     enabled
    0.06
    -quote
    0.06
     Вид
    0.06
     permitting
    0.06
    =forms
    0.06
     restrained
    0.06
     врем
    0.06
     serait
    0.06
    Act Density 0.027%

    No Known Activations