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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash

    This neuron detects legal-claim phrases expressing that a party “is entitled to” something.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     crawled
    -0.06
     actually
    -0.06
     it
    -0.06
    .setLayoutParams
    -0.06
     porous
    -0.06
     showcases
    -0.06
    (cin
    -0.06
     &)
    -0.06
     wrote
    -0.06
     fun
    -0.06
    POSITIVE LOGITS
    register
    0.07
    jourd
    0.07
    semi
    0.07
     demonstr
    0.07
    Ģ
    0.06
     주
    0.06
    eken
    0.06
    underline
    0.06
    wrapper
    0.06
    ена
    0.06
    Act Density 0.012%

    No Known Activations