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

    Neuronpedia

    INDEX
    Explanations

    _width

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric layout dimension values in Android XML (e.g. the floating‐point numbers for android:layout_width and android:layout_height).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     चलत
    -0.07
     Imperial
    -0.06
     Scot
    -0.06
    وبة
    -0.06
    urring
    -0.06
     reaction
    -0.06
    cust
    -0.06
     Imper
    -0.06
     Kon
    -0.06
     HOR
    -0.06
    POSITIVE LOGITS
    _components
    0.07
     appBar
    0.07
    igInteger
    0.07
     العم
    0.07
    _width
    0.07
    SetName
    0.07
    -sama
    0.06
    atatype
    0.06
     screenWidth
    0.06
    _firstname
    0.06
    Act Density 0.001%

    No Known Activations