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

    Neuronpedia

    INDEX
    Explanations

    process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proceedings
    -0.08
     eens
    -0.08
     bonds
    -0.07
    瑪
    -0.07
     evenly
    -0.06
    ichael
    -0.06
     curiosity
    -0.06
    (Expected
    -0.06
    🍼
    -0.06
    Credits
    -0.06
    POSITIVE LOGITS
    �
    0.07
     NSK
    0.07
    遥远
    0.07
    联络
    0.07
    desk
    0.07
    اصر
    0.07
    Unary
    0.07
    asm
    0.06
    や
    0.06
     Nearby
    0.06
    Act Density 0.033%

    No Known Activations