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 activates on references to Android permissions APIs—e.g. Manifest.permission tokens, PackageManager.PERMISSION_* constants, and calls to checkSelfPermission/requestPermissions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    xD
    -0.07
     zwei
    -0.06
    onds
    -0.06
     přid
    -0.06
    あり
    -0.06
     ett
    -0.06
     chips
    -0.06
    fld
    -0.06
     nay
    -0.06
    XE
    -0.06
    POSITIVE LOGITS
    .PERMISSION
    0.07
    Really
    0.06
    €™
    0.06
     Fl
    0.06
    accom
    0.06
     explaining
    0.06
    ‌کنندگان
    0.06
     Monster
    0.06
    minimum
    0.06
    $string
    0.06
    Act Density 0.000%

    No Known Activations