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

    Neuronpedia

    INDEX
    Explanations

    code and configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     announcing
    -0.07
    gross
    -0.06
     流
    -0.06
     Alamofire
    -0.06
     steam
    -0.06
     hrs
    -0.06
    ，小
    -0.06
    alarm
    -0.06
    �示
    -0.06
     sleeping
    -0.06
    POSITIVE LOGITS
     prosperity
    0.06
     trouvé
    0.06
     Bunu
    0.06
     　　　　　　　　　　　　
    0.06
    leshooting
    0.06
     Beginner
    0.06
    cının
    0.06
     Wax
    0.06
     множе
    0.06
     venda
    0.06
    Act Density 0.145%

    No Known Activations