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

    Neuronpedia

    INDEX
    Explanations

    Obama

    np_max-act · gemini-2.0-flash

    The neuron primarily detects occurrences of the name “Obama.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    乱
    -0.07
     fern
    -0.07
     Fern
    -0.06
     Jain
    -0.06
     Declare
    -0.06
     대
    -0.06
    	synchronized
    -0.06
     Glen
    -0.06
    tec
    -0.06
    =R
    -0.06
    POSITIVE LOGITS
    Obama
    0.13
     Obama
    0.13
     Hollande
    0.08
     Barack
    0.08
    abe
    0.08
     Beckham
    0.07
    ODO
    0.07
     Oprah
    0.07
    iggins
    0.07
    imdi
    0.07
    Act Density 0.007%

    No Known Activations