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

    Neuronpedia

    INDEX
    Explanations

    because

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on the causal connective “because.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     však
    -0.06
    theorem
    -0.06
    ็อก
    -0.06
     недели
    -0.06
     Maar
    -0.06
    .appspot
    -0.06
    _five
    -0.06
     Ingram
    -0.05
    	clock
    -0.05
    dock
    -0.05
    POSITIVE LOGITS
    Rus
    0.07
     as
    0.07
    +");↵
    0.07
     effet
    0.07
     ru
    0.07
     influenza
    0.07
    「え
    0.06
    /apple
    0.06
     rim
    0.06
     figured
    0.06
    Act Density 0.044%

    No Known Activations