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

    Neuronpedia

    INDEX
    Explanations

    group

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tre
    -0.07
    Explore
    -0.07
     Ever
    -0.07
     Custom
    -0.07
    Do
    -0.07
     eve
    -0.07
    -validation
    -0.07
     Grand
    -0.07
    Have
    -0.07
    鸿
    -0.07
    POSITIVE LOGITS
     jets
    0.08
    avery
    0.07
    Ż
    0.07
     kết
    0.07
    יס
    0.07
     Braves
    0.07
    .AddField
    0.06
    㛃
    0.06
     phạm
    0.06
     chiefly
    0.06
    Act Density 0.012%

    No Known Activations