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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _repo
    -0.07
    .ReadAllText
    -0.06
     Tales
    -0.06
     其他
    -0.06
    ця
    -0.06
    복
    -0.06
    ItemSelected
    -0.06
    目录
    -0.06
     periodo
    -0.06
    -mouth
    -0.06
    POSITIVE LOGITS
     concert
    0.08
    596
    0.07
     marches
    0.07
     appointed
    0.06
     defending
    0.06
     sailing
    0.06
     svých
    0.06
     BIND
    0.06
    VRT
    0.06
     announce
    0.06
    Act Density 0.001%

    No Known Activations