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

    Neuronpedia

    INDEX
    Explanations

    news stories and legal cases

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are parts of personal proper names, i.e. it detects people’s names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ging
    -0.06
     manager
    -0.06
    SetTitle
    -0.06
    492
    -0.06
    @Transactional
    -0.06
    .Word
    -0.06
     เด
    -0.06
    ₀
    -0.06
    StringLength
    -0.06
    aload
    -0.06
    POSITIVE LOGITS
     fans
    0.07
     ferment
    0.07
    dsa
    0.07
     AW
    0.07
     cliff
    0.07
     demek
    0.07
    neck
    0.07
    Hdr
    0.07
    lement
    0.07
    าษฎ
    0.07
    Act Density 0.006%

    No Known Activations