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

    Neuronpedia

    INDEX
    Explanations

    layout

    np_max-act · gemini-2.0-flash

    The neuron fires on the floating‐point numbers used in Android XML layout attributes (e.g. the decimal values assigned to android:layout_width, layout_height, layout_weight, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    errick
    -0.08
    .listFiles
    -0.07
    anchors
    -0.06
    >T
    -0.06
    FG
    -0.06
    _GET
    -0.06
    .alert
    -0.06
     Kunden
    -0.06
    contre
    -0.06
    _integral
    -0.06
    POSITIVE LOGITS
     Floating
    0.07
     Years
    0.06
    dbname
    0.06
     YEARS
    0.06
     Occasionally
    0.06
     went
    0.06
     vaguely
    0.06
     Проф
    0.06
    entral
    0.06
    /********************************************************
    0.06
    Act Density 0.001%

    No Known Activations