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

    Neuronpedia

    INDEX
    Explanations

    Trick-taking games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recomendado
    -0.08
     restrained
    -0.08
     элект
    -0.08
    畅
    -0.08
     autorizado
    -0.08
    报警
    -0.08
     recomenda
    -0.08
    _PRODUCT
    -0.07
    科学
    -0.07
    Restart
    -0.07
    POSITIVE LOGITS
     possession
    0.10
     Ownership
    0.10
     allegiance
    0.10
    Ownership
    0.09
     ownership
    0.09
     winnings
    0.09
     bidders
    0.08
     Votes
    0.08
    claim
    0.08
     bidder
    0.08
    Act Density 0.013%

    No Known Activations