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

    Neuronpedia

    INDEX
    Explanations

    inflater

    np_max-act · gemini-2.0-flash

    This neuron detects Android layout‐inflation calls (e.g. uses of a LayoutInflater’s inflate method and related “layout” tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cultura
    -0.06
    .lock
    -0.06
     commute
    -0.06
    /catalog
    -0.06
    .label
    -0.06
    \xe
    -0.06
    .norm
    -0.06
    -ready
    -0.06
    ió
    -0.06
    �a
    -0.06
    POSITIVE LOGITS
     inflater
    0.11
    LayoutInflater
    0.08
    .LayoutInflater
    0.07
     filler
    0.07
    (inflater
    0.07
     getMenuInflater
    0.07
     savedInstanceState
    0.07
     temperatures
    0.07
     LayoutInflater
    0.07
     initialization
    0.06
    Act Density 0.001%

    No Known Activations