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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mga
    -0.07
    "})
    -0.07
    四项
    -0.07
    斥
    -0.07
    ıld
    -0.07
     TODO
    -0.07
     roadmap
    -0.07
     indexPath
    -0.07
    汹
    -0.07
    sip
    -0.07
    POSITIVE LOGITS
    售票
    0.07
     blue
    0.06
    朳
    0.06
    澂
    0.06
     Terminal
    0.06
     Congo
    0.06
     Entries
    0.06
    纵深
    0.06
    .finish
    0.06
    aise
    0.06
    Act Density 0.005%

    No Known Activations