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

    Neuronpedia

    INDEX
    Explanations

    White House, president

    np_max-act · gemini-2.0-flash

    The neuron is strongly activated by words naming political offices, institutions, and high‐level government or electoral entities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    愿
    -0.07
    tak
    -0.07
    borne
    -0.06
    Asian
    -0.06
     broker
    -0.06
     sop
    -0.06
    CELL
    -0.06
     Brock
    -0.06
    sex
    -0.06
    for
    -0.06
    POSITIVE LOGITS
    ной
    0.07
    ernetes
    0.06
     ž
    0.06
    ナ
    0.06
    図
    0.06
    odář
    0.06
    ;↵↵↵
    0.06
     inorder
    0.06
     Bí
    0.06
    datum
    0.06
    Act Density 0.039%

    No Known Activations