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

    Neuronpedia

    INDEX
    Explanations

    biographical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stunden
    -0.07
     courageous
    -0.07
    .Th
    -0.06
     diseñador
    -0.06
     příro
    -0.06
    unar
    -0.06
    柏
    -0.06
    .If
    -0.06
    İSİ
    -0.06
    _master
    -0.06
    POSITIVE LOGITS
    levant
    0.07
     masse
    0.07
     CONTEXT
    0.06
     (%)
    0.06
    (Key
    0.06
    这里
    0.06
     tận
    0.06
    Pos
    0.06
    Western
    0.06
    گونه
    0.06
    Act Density 0.051%

    No Known Activations