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

    Neuronpedia

    INDEX
    Explanations

    Kubernetes deployments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    うち
    -0.07
    춘
    -0.07
    Arena
    -0.06
     yaz
    -0.06
    数据库
    -0.06
     önünde
    -0.06
    ioned
    -0.06
     multim
    -0.06
    ast
    -0.06
    silver
    -0.06
    POSITIVE LOGITS
     freq
    0.07
     decorator
    0.07
    utor
    0.07
    ffffffff
    0.07
     пак
    0.06
     startups
    0.06
    request
    0.06
    orney
    0.06
    }else
    0.06
     reckless
    0.06
    Act Density 0.012%

    No Known Activations