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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lur
    -0.07
     kil
    -0.07
     prepaid
    -0.07
     gor
    -0.07
    政府
    -0.06
     数据
    -0.06
    控制
    -0.06
     pollution
    -0.06
    .ToShort
    -0.06
    cl
    -0.06
    POSITIVE LOGITS
    Separator
    0.06
    _kategori
    0.06
     "),↵
    0.06
     enhances
    0.06
     edx
    0.06
    (_
    0.06
    DeltaTime
    0.06
    ")
    0.06
    ourke
    0.06
    _iface
    0.06
    Act Density 0.152%

    No Known Activations