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

    Neuronpedia

    INDEX
    Explanations

    Class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    申报
    -0.07
    חשב
    -0.07
     yours
    -0.07
    .re
    -0.07
    ```
    -0.06
     expand
    -0.06
     excerpts
    -0.06
    的独特
    -0.06
     opt
    -0.06
    ']))↵↵
    -0.06
    POSITIVE LOGITS
    Symbols
    0.07
     Spicer
    0.07
    (Symbol
    0.07
    向东
    0.07
    rowave
    0.07
    ױ
    0.07
     Logger
    0.06
     mqtt
    0.06
    控制系统
    0.06
     Syracuse
    0.06
    Act Density 0.000%

    No Known Activations