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

    Neuronpedia

    INDEX
    Explanations

    proxy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Milton
    -0.08
     Hill
    -0.08
     Samuel
    -0.07
     radically
    -0.07
    837
    -0.07
    .collection
    -0.07
     Mont
    -0.07
     chemistry
    -0.06
    PUTE
    -0.06
     Nationwide
    -0.06
    POSITIVE LOGITS
     Proxy
    0.09
    Proxy
    0.08
    екси
    0.08
    proxy
    0.08
     proxies
    0.07
    代理
    0.07
    博
    0.07
    ไม
    0.07
     backpack
    0.07
    edis
    0.07
    Act Density 0.007%

    No Known Activations