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

    Neuronpedia

    INDEX
    Explanations

    deployment and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     சிற்ப
    0.38
     Granger
    0.38
     conservation
    0.37
     investigative
    0.37
    माटर
    0.37
     Morrow
    0.36
     Nicholson
    0.36
     engra
    0.35
     Sandoval
    0.35
    วิต
    0.35
    POSITIVE LOGITS
    deploy
    1.19
     deploy
    1.16
     Deploy
    1.14
     deployment
    1.13
    Deploy
    1.10
     deployments
    1.09
     deploying
    1.07
     Deployment
    1.05
    部署
    1.02
    Deployment
    1.02
    Act Density 0.017%

    No Known Activations