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

    Neuronpedia

    INDEX
    Explanations

    Satire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    营业
    -0.07
     Champion
    -0.07
     ermög
    -0.07
    Bonus
    -0.06
     intrusive
    -0.06
     Insp
    -0.06
    合作
    -0.06
    oras
    -0.06
     clot
    -0.06
     круп
    -0.06
    POSITIVE LOGITS
     satire
    0.10
     parody
    0.07
    ัฐ
    0.07
    енных
    0.06
     critically
    0.06
     الدر
    0.06
     precis
    0.06
    англ
    0.06
     successive
    0.06
     tarihi
    0.06
    Act Density 0.007%

    No Known Activations