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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash

    The neuron fires on Android XML layout markup—i.e. it detects the `<…>` tags and their `android:…` attributes in layout files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     foul
    -0.06
    aits
    -0.06
     usable
    -0.06
    ]]
↵
    -0.06
    .")
↵
    -0.06
     توق
    -0.06
    �
    -0.06
    ($(".
    -0.06
     πάνω
    -0.06
     życ
    -0.06
    POSITIVE LOGITS
     biri
    0.07
    /lgpl
    0.07
    laması
    0.07
    (Dialog
    0.07
    ----------------------------------------------------------------------------
    0.06
    ########################################################
    0.06
    /{{$
    0.06
    Indented
    0.06
    (PyObject
    0.06
     carb
    0.06
    Act Density 0.001%

    No Known Activations