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

    Neuronpedia

    INDEX
    Explanations

    Astrology and rulership

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _expect
    -0.07
    (Me
    -0.06
     מכל
    -0.06
     Pour
    -0.06
    生态环境
    -0.06
    FromDate
    -0.06
    动静
    -0.06
     embar
    -0.06
     ana
    -0.06
     cents
    -0.06
    POSITIVE LOGITS
    託
    0.08
    token
    0.07
    .abs
    0.07
    쉘
    0.07
     assists
    0.07
    .tokens
    0.07
    OLUMN
    0.07
    私立
    0.07
    持有的
    0.07
     الجامعة
    0.07
    Act Density 0.013%

    No Known Activations