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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    natal
    -0.08
     mills
    -0.08
    checks
    -0.07
    Big
    -0.07
    学习
    -0.07
    _edit
    -0.06
    password
    -0.06
    biz
    -0.06
    .Download
    -0.06
    Increasing
    -0.06
    POSITIVE LOGITS
     trang
    0.07
    戶
    0.06
     रन
    0.06
     finanční
    0.06
     parten
    0.06
    _compress
    0.06
     Qi
    0.06
    kategori
    0.06
     seize
    0.06
    findViewById
    0.06
    Act Density 0.001%

    No Known Activations