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

    Neuronpedia

    INDEX
    Explanations

    Geographic locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ourage
    -0.07
     Κό
    -0.07
    _ports
    -0.06
    うち
    -0.06
     уров
    -0.06
    δρο
    -0.06
    .Dropout
    -0.06
    ователь
    -0.06
    peri
    -0.06
    子供
    -0.06
    POSITIVE LOGITS
      ↵  ↵
    0.07
    lili
    0.07
    _requests
    0.06
    /Game
    0.06
     От
    0.06
     Naomi
    0.06
    品牌
    0.06
     Όμιλος
    0.06
     sockets
    0.06
    uld
    0.06
    Act Density 0.036%

    No Known Activations