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

    Neuronpedia

    INDEX
    Explanations

    contract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     knowledge
    -0.07
     geo
    -0.07
     zombies
    -0.07
     Yi
    -0.07
     Knowledge
    -0.07
     aided
    -0.07
     Poh
    -0.06
    _root
    -0.06
     meditation
    -0.06
     aid
    -0.06
    POSITIVE LOGITS
     contract
    0.10
    contracts
    0.09
     Contract
    0.09
     contracts
    0.09
    合同
    0.07
    Contract
    0.07
    )(↵
    0.07
     عقد
    0.07
     dbContext
    0.07
    amacare
    0.07
    Act Density 0.020%

    No Known Activations