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

    Neuronpedia

    INDEX
    Explanations

    operations and languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
     ẹ
    -0.08
     noct
    -0.08
     discretionary
    -0.08
     influential
    -0.07
     살
    -0.07
    verbosity
    -0.07
    Disposable
    -0.07
     circonstances
    -0.07
     summertime
    -0.07
    POSITIVE LOGITS
     interoperability
    0.17
     interoper
    0.17
     بينها
    0.14
     seamless
    0.13
     exchanging
    0.12
     между
    0.12
     بينهم
    0.12
    通信
    0.12
     seamlessly
    0.12
     ನಡುವೆ
    0.12
    Act Density 0.024%
    No Known Activations