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

    Neuronpedia

    INDEX
    Explanations

    Bot frameworks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ROS
    -0.07
     Tut
    -0.07
     homem
    -0.07
     пері
    -0.07
     pozn
    -0.06
    Cette
    -0.06
     grpc
    -0.06
    .AdapterView
    -0.06
    Cadastro
    -0.06
     Mou
    -0.06
    POSITIVE LOGITS
    level
    0.07
    tent
    0.07
     bakım
    0.06
     theoretically
    0.06
    urv
    0.06
    reements
    0.06
     notation
    0.06
    Ross
    0.06
    "\↵
    0.06
    imi
    0.06
    Act Density 0.002%

    No Known Activations