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

    Neuronpedia

    INDEX
    Explanations

    groups of people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ién
    -0.06
    Scoped
    -0.06
     networks
    -0.06
     Dub
    -0.06
     Nab
    -0.06
    рож
    -0.06
    �
    -0.06
     다른
    -0.06
    沟
    -0.06
    ैं।
    -0.06
    POSITIVE LOGITS
     FHA
    0.07
    +↵
    0.07
    ผม
    0.06
     아래
    0.06
    (GLFW
    0.06
    ΕΚ
    0.06
     agosto
    0.06
    nes
    0.06
     перем
    0.06
     لباس
    0.06
    Act Density 0.056%

    No Known Activations