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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals in Android layout/XML code (e.g. dimension values, resource IDs, weights).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     utilisateur
    -0.07
     casos
    -0.07
    ảng
    -0.07
    교회
    -0.07
     Hen
    -0.07
    �
    -0.06
    CollectionView
    -0.06
    ̆
    -0.06
     ум
    -0.06
     fonts
    -0.06
    POSITIVE LOGITS
    _private
    0.06
    [List
    0.06
     Marco
    0.06
    .php
    0.06
    lixir
    0.06
     Minecraft
    0.06
    енного
    0.06
     realized
    0.06
     tolerated
    0.06
    =self
    0.05
    Act Density 0.001%

    No Known Activations