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

    Neuronpedia

    INDEX
    Explanations

    William

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the proper name “William.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    in
    -0.07
    IN
    -0.07
     SO
    -0.07
    ein
    -0.07
    oo
    -0.06
    1
    -0.06
     Shia
    -0.06
     CN
    -0.06
    _Real
    -0.06
    oin
    -0.06
    POSITIVE LOGITS
    James
    0.12
     James
    0.11
     Frederick
    0.10
     Charles
    0.09
     Lawrence
    0.09
     William
    0.09
    Charles
    0.09
    AMES
    0.09
    William
    0.09
     Samuel
    0.09
    Act Density 0.075%

    No Known Activations