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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron identifies personal names—sequences of capitalized tokens representing individuals’ names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    perimental
    -0.07
     Jews
    -0.07
    urf
    -0.07
     tested
    -0.07
    igos
    -0.06
     qreal
    -0.06
     Sword
    -0.06
    fetch
    -0.06
    riends
    -0.06
    fas
    -0.06
    POSITIVE LOGITS
    MITTED
    0.06
    .CO
    0.06
    mlx
    0.06
     ослож
    0.06
     ως
    0.06
     دیگر
    0.06
     MQ
    0.06
     cheque
    0.06
     싱
    0.06
     Mev
    0.06
    Act Density 0.016%

    No Known Activations