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

    Neuronpedia

    INDEX
    Explanations

    tournament graphs and cycles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Homes
    -0.08
    vara
    -0.08
    妈妈
    -0.08
    ెన
    -0.08
    Plans
    -0.08
    Sans
    -0.08
     Família
    -0.08
    家庭
    -0.07
     familia
    -0.07
    Maison
    -0.07
    POSITIVE LOGITS
     rankings
    0.11
     victories
    0.11
     undefeated
    0.11
     જીત
    0.11
     winner
    0.11
     ranking
    0.10
     tournament
    0.10
    ournament
    0.10
    -ranking
    0.10
     defeated
    0.10
    Act Density 0.012%

    No Known Activations