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

    Neuronpedia

    INDEX
    Explanations

    answers to questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     notation
    -0.07
     jsonArray
    -0.07
    为什么
    -0.07
     chiefly
    -0.07
    _linear
    -0.07
    тер
    -0.06
     ★
    -0.06
     soils
    -0.06
     waves
    -0.06
    .JSONObject
    -0.06
    POSITIVE LOGITS
     شرکت
    0.06
    ied
    0.06
    -news
    0.06
    /Admin
    0.06
    україн
    0.06
    orny
    0.06
    ",__
    0.05
     Troll
    0.05
    ALLY
    0.05
     능
    0.05
    Act Density 0.084%

    No Known Activations