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

    Neuronpedia

    INDEX
    Explanations

    js

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     terse
    -0.07
     그림
    -0.07
     เน
    -0.06
     परम
    -0.06
     Communic
    -0.06
    ohen
    -0.06
    ()↵↵
    -0.06
    _THE
    -0.06
     �
    -0.06
    odi
    -0.06
    POSITIVE LOGITS
     DDR
    0.07
     за
    0.06
     []
    0.06
     ><?
    0.06
    是我
    0.06
    工具
    0.06
    PDOException
    0.06
    ۲۸
    0.06
     eskorte
    0.06
    tls
    0.06
    Act Density 0.002%

    No Known Activations