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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gul
    -0.08
    um
    -0.08
     용
    -0.07
    Um
    -0.07
     um
    -0.07
     응
    -0.07
     pulp
    -0.07
     Nug
    -0.07
     คำ
    -0.07
     �
    -0.07
    POSITIVE LOGITS
      ↵
    0.10
      ↵↵
    0.08
    西
    0.07
      ↵
    0.07
     Sierra
    0.07
         ↵
    0.07
    789
    0.07
      ↵↵↵
    0.07
      ↵
    0.07
     zbo
    0.07
    Act Density 0.018%

    No Known Activations