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

    Neuronpedia

    INDEX
    Explanations

    legal language

    np_max-act · gemini-2.0-flash

    This neuron detects formal legal‐contract scope phrases that qualify or limit rights (e.g. “directly pertinent to the contracts”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -reported
    -0.06
     Ernest
    -0.06
     Resume
    -0.06
     печ
    -0.06
     reported
    -0.06
    istrat
    -0.05
    Senate
    -0.05
    Access
    -0.05
    <E
    -0.05
    (mutex
    -0.05
    POSITIVE LOGITS
     β
    0.07
    ftware
    0.07
    ğinde
    0.07
    .experimental
    0.06
    .getLongitude
    0.06
    .Platform
    0.06
    _logits
    0.06
    \"",↵
    0.06
    čních
    0.06
    getRepository
    0.06
    Act Density 0.024%

    No Known Activations