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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    logg
    -0.08
     Rope
    -0.07
    /shop
    -0.07
     komen
    -0.07
    Submission
    -0.07
    📞
    -0.07
    .targets
    -0.07
    svm
    -0.07
    Winner
    -0.07
     Scope
    -0.07
    POSITIVE LOGITS
     关
    0.07
    (ur
    0.07
     де
    0.07
     adjacency
    0.07
    给人一种
    0.07
     �
    0.07
    遐
    0.07
                    ↵
    0.07
    퉁
    0.06
    .bucket
    0.06
    Act Density 0.003%

    No Known Activations