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

    Neuronpedia

    INDEX
    Explanations

    court documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    哎
    -0.07
    .Active
    -0.07
     haystack
    -0.07
    addir
    -0.06
    ("").
    -0.06
    鋆
    -0.06
    共同努力
    -0.06
    翼
    -0.06
    etr
    -0.06
    _FILE
    -0.06
    POSITIVE LOGITS
    變成
    0.08
    PDO
    0.08
    跑到
    0.08
    cion
    0.07
     surfing
    0.07
     Sphinx
    0.07
     Territory
    0.07
    WithContext
    0.07
    PBS
    0.07
     forecasting
    0.06
    Act Density 0.001%

    No Known Activations