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

    Neuronpedia

    INDEX
    Explanations

    quit

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the verb “quit” (including “quit,” “quitting,” etc.), i.e. mentions of giving up or stopping an activity.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     досвід
    -0.07
    _HP
    -0.07
     ortam
    -0.07
    kemiz
    -0.07
     sensory
    -0.07
    地域
    -0.07
     embody
    -0.06
    амет
    -0.06
    rede
    -0.06
     uomini
    -0.06
    POSITIVE LOGITS
     quit
    0.13
     Quit
    0.09
     quits
    0.09
     quitting
    0.09
    Quit
    0.07
     Juliet
    0.07
    940
    0.07
    quest
    0.07
     join
    0.07
    现在
    0.06
    Act Density 0.002%

    No Known Activations