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

    Neuronpedia

    INDEX
    Explanations

    Android function names

    np_max-act · gemini-2.0-flash

    This neuron detects Android component callback method names, especially lifecycle (`onAttach`, `onCreate`) and menu‐related (`onCreateOptionsMenu`, `onOptionsItemSelected`) overrides.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    帖
    -0.07
    습니다
    -0.06
    _resp
    -0.06
     meditation
    -0.06
     AppDelegate
    -0.06
     climbers
    -0.06
     bombs
    -0.06
     crates
    -0.06
    voří
    -0.06
    .***.***
    -0.06
    POSITIVE LOGITS
     viele
    0.07
     misled
    0.07
    >{$
    0.07
    итор
    0.07
     także
    0.06
     discussing
    0.06
     DJs
    0.06
    getText
    0.06
    eus
    0.06
    .vertx
    0.06
    Act Density 0.015%

    No Known Activations