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

    Neuronpedia

    INDEX
    Explanations

    worker-managed economics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     score
    -0.08
     Geographic
    -0.08
     oceans
    -0.08
     zodiac
    -0.08
    ಡ್ಡ
    -0.08
     démar
    -0.07
     penalty
    -0.07
     Arctic
    -0.07
     ocean
    -0.07
     piercing
    -0.07
    POSITIVE LOGITS
     коллектив
    0.10
     democratic
    0.10
     demokr
    0.09
     തൊഴില
    0.09
     grassroots
    0.09
     vrijwill
    0.09
     democrática
    0.09
     empowered
    0.09
     लोकत
    0.09
     тру
    0.09
    Act Density 0.023%

    No Known Activations