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

    Neuronpedia

    INDEX
    Explanations

    court

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on the token “Court,” detecting that exact word whenever it appears.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    biên
    -0.06
     دختر
    -0.06
     Gry
    -0.06
     Neh
    -0.06
    igth
    -0.06
    (which
    -0.06
     момент
    -0.06
    floor
    -0.06
     Reef
    -0.05
    'name
    -0.05
    POSITIVE LOGITS
    .PrimaryKey
    0.07
    .SaveChanges
    0.07
    password
    0.07
    Total
    0.07
     afternoon
    0.07
    endars
    0.06
    loha
    0.06
    ISTIC
    0.06
     Coupon
    0.06
    _SR
    0.06
    Act Density 0.004%

    No Known Activations