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

    Neuronpedia

    INDEX
    Explanations

    Technical/formal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itimate
    -0.08
     bid
    -0.07
    앚
    -0.07
     Lal
    -0.07
     timed
    -0.07
    winner
    -0.07
     né
    -0.07
     Vinyl
    -0.07
     sworn
    -0.07
    .disabled
    -0.07
    POSITIVE LOGITS
     deployments
    0.08
     documentation
    0.07
    科學
    0.07
     Kanye
    0.07
     proto
    0.07
     objectMapper
    0.07
    教育资源
    0.07
    广东省
    0.07
    广州市
    0.07
     прод
    0.06
    Act Density 0.145%

    No Known Activations