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

    Neuronpedia

    INDEX
    Explanations

    labs, media, and making

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     triglycer
    -0.09
     Bundesliga
    -0.08
     nier
    -0.08
     Croatian
    -0.08
     Ucr
    -0.08
     rusa
    -0.08
     Midland
    -0.08
     Cash
    -0.08
     releg
    -0.08
     acne
    -0.08
    POSITIVE LOGITS
     hackers
    0.10
     hacker
    0.10
     interdisciplinary
    0.10
     interdiscip
    0.10
    Universe
    0.10
     remix
    0.09
     neuroscience
    0.09
     humanities
    0.09
    innovation
    0.09
     hacking
    0.09
    Act Density 0.084%

    No Known Activations