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

    Neuronpedia

    INDEX
    Explanations

    Jeffrey/Rey

    np_max-act · gemini-2.0-flash

    This neuron specifically detects occurrences of the proper name “Jeffrey.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    104
    -0.08
    20
    -0.07
    ₂
    -0.07
    168
    -0.07
     loan
    -0.07
     glass
    -0.07
    장
    -0.07
     pot
    -0.07
     small
    -0.07
     Bottle
    -0.07
    POSITIVE LOGITS
     Jeff
    0.10
     Morris
    0.09
    Jeff
    0.08
    ).↵
    0.08
     (
    0.08
    Ken
    0.08
     Mor
    0.08
    .↵
    0.07
     Geoff
    0.07
     skate
    0.07
    Act Density 0.070%

    No Known Activations