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

    Neuronpedia

    INDEX
    Explanations

    _content

    np_max-act · gemini-2.0-flash

    This neuron fires on Android XML layout dimension and sizing attributes (e.g. “wrap_content,” “match_parent,” numeric values with “dp”/“sp”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     maz
    -0.07
    UTERS
    -0.07
    groupBy
    -0.06
     Hats
    -0.06
     männer
    -0.06
    Pos
    -0.06
     Pa
    -0.06
    arkers
    -0.06
     pa
    -0.06
     zak
    -0.06
    POSITIVE LOGITS
    عه
    0.08
    (TreeNode
    0.07
    ğını
    0.07
    空间
    0.06
    .faces
    0.06
    حی
    0.06
     Content
    0.06
     postData
    0.06
     olmadığı
    0.06
    unden
    0.06
    Act Density 0.001%

    No Known Activations