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

    Neuronpedia

    INDEX
    Explanations

    .intent

    np_max-act · gemini-2.0-flash

    The neuron activates on Android manifest intent filters—specifically tokens beginning with “android.intent” in action and category declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Seat
    -0.07
    Gate
    -0.06
    _km
    -0.06
    staking
    -0.06
     fatigue
    -0.06
    Acceleration
    -0.06
    	sm
    -0.06
    testCase
    -0.06
    	var
    -0.06
     collision
    -0.06
    POSITIVE LOGITS
    них
    0.07
    )];↵
    0.07
     تخصص
    0.07
    ]++;↵
    0.07
       
    0.07
     зависимости
    0.06
    123
    0.06
     Bruins
    0.06
    ](
    0.06
     FOOT
    0.06
    Act Density 0.000%

    No Known Activations