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

    Neuronpedia

    INDEX
    Explanations

    .permission

    np_max-act · gemini-2.0-flash

    The neuron detects Android manifest permission entries (i.e. lines specifying android.permission.*).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    折
    -0.07
     Another
    -0.07
     UIStoryboard
    -0.06
    間
    -0.06
    聚
    -0.06
    وینت
    -0.06
     Arcade
    -0.06
     WR
    -0.06
    12
    -0.06
     \\
    -0.06
    POSITIVE LOGITS
    .permission
    0.10
    .PropertyType
    0.07
    gün
    0.07
    -border
    0.07
    	Con
    0.07
    ROME
    0.07
    0.07
     perpetual
    0.07
    JV
    0.07
     zel
    0.07
    Act Density 0.000%

    No Known Activations