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

    Neuronpedia

    INDEX
    Explanations

    Launch

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on the “handle” token in Android exception stack traces, particularly in the call to ActivityThread.handleLaunchActivity.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     panties
    -0.06
     Clubs
    -0.06
     Sew
    -0.06
     shooter
    -0.06
     Readonly
    -0.06
     fluid
    -0.06
     standardized
    -0.06
    贸
    -0.06
    Heat
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    (ViewGroup
    0.08
    Chain
    0.08
     Pics
    0.07
     срок
    0.07
    {return
    0.07
     noen
    0.06
    currently
    0.06
     brutality
    0.06
    ecimal
    0.06
    рок
    0.06
    Act Density 0.000%

    No Known Activations