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

    Neuronpedia

    INDEX
    Explanations

    .category

    np_max-act · gemini-2.0-flash

    The neuron fires on the XML “category” lines in Android manifest files (e.g. the `<category android:name="android.intent.category.LAUNCHER">` entries).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (sim
    -0.08
     Pokémon
    -0.07
     suprem
    -0.06
     Animalia
    -0.06
     النظام
    -0.06
    疾
    -0.06
    ону
    -0.06
    成绩
    -0.06
    �
    -0.06
     poisoning
    -0.06
    POSITIVE LOGITS
    .category
    0.09
    ........
    0.07
     /^
    0.07
    0.06
    Filed
    0.06
     uniq
    0.06
    -save
    0.06
    ย
    0.06
    _PERIOD
    0.06
    ンティ
    0.06
    Act Density 0.000%

    No Known Activations