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

    Neuronpedia

    INDEX
    Explanations

    Strat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flows
    -0.07
     slice
    -0.07
     glob
    -0.06
    	node
    -0.06
    ouncil
    -0.06
     único
    -0.06
    _DAC
    -0.06
     drive
    -0.06
     Agu
    -0.06
     tax
    -0.06
    POSITIVE LOGITS
    Seriously
    0.07
    んど
    0.07
     comprehensive
    0.07
     miserable
    0.06
     createStackNavigator
    0.06
     Seriously
    0.06
    sem
    0.06
    	logging
    0.06
    プラ
    0.06
    ">',
    0.06
    Act Density 0.002%

    No Known Activations