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

    Neuronpedia

    INDEX
    Explanations

    Names/administrative/sports contexts

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is pick out administrative or governmental office titles (e.g. “acting,” “Governor-General,” “Administrator,” “Commissioner,” “Lieutenant”), signaling references to official positions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     photographed
    -0.08
     narrowed
    -0.07
    Legendary
    -0.06
     právní
    -0.06
     Beta
    -0.06
     architekt
    -0.06
    勒
    -0.06
    nis
    -0.06
     WHAT
    -0.06
     Wolverine
    -0.06
    POSITIVE LOGITS
     races
    0.07
    OfSize
    0.07
    _nth
    0.06
    ouse
    0.06
    ійного
    0.06
    rof
    0.06
     senza
    0.06
     au
    0.06
     Sum
    0.06
    .dense
    0.06
    Act Density 0.052%

    No Known Activations