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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash

    The neuron activates when it sees the substring “apk,” i.e. references to APK in Android XML files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Playback
    -0.07
    gmt
    -0.06
     dma
    -0.06
     colleagues
    -0.06
     찬
    -0.06
     Πο
    -0.06
    Carousel
    -0.06
    _WRAPPER
    -0.06
    Foo
    -0.06
    Ten
    -0.06
    POSITIVE LOGITS
     router
    0.06
     Manning
    0.06
    ucc
    0.06
     只
    0.06
     Constructor
    0.06
     Earth
    0.06
    KA
    0.06
     compens
    0.06
     крок
    0.06
     armed
    0.06
    Act Density 0.000%

    No Known Activations