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
     junto
    -0.07
    助
    -0.07
     варт
    -0.07
     cộng
    -0.07
     bırak
    -0.07
     Ast
    -0.07
     Provision
    -0.06
    �乐
    -0.06
    ůž
    -0.06
     없어
    -0.06
    POSITIVE LOGITS
    "To
    0.06
    >Delete
    0.06
    redicate
    0.06
    �
    0.06
    .setSelection
    0.06
      
↵
    0.06
    ेदन
    0.06
    حر
    0.06
    .Sequential
    0.06
     tướng
    0.06
    Act Density 0.072%

    No Known Activations