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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qualche
    -0.08
     tienes
    -0.07
    county
    -0.07
    吃了
    -0.07
     exemplo
    -0.07
    _TYP
    -0.07
    Jean
    -0.07
    邱
    -0.07
    .ext
    -0.07
    olie
    -0.06
    POSITIVE LOGITS
    محاكم
    0.07
     daemon
    0.07
     gọn
    0.07
    .amazonaws
    0.07
    密封
    0.06
     Fiona
    0.06
    平均
    0.06
    ยาว
    0.06
    מטפל
    0.06
     cares
    0.06
    Act Density 0.034%

    No Known Activations