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

    Neuronpedia

    INDEX
    Explanations

    incomplete/partial texts or code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orc
    -0.06
     JSX
    -0.06
    Tu
    -0.06
     boil
    -0.06
     volatility
    -0.06
    .LoggerFactory
    -0.06
     إلي
    -0.06
    ())
↵
    -0.06
     pinned
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    YNAMIC
    0.07
     Using
    0.07
    verages
    0.07
    arlo
    0.07
     Zach
    0.06
    ΕΡ
    0.06
    ING
    0.06
    ゴリ
    0.06
     창
    0.06
    �
    0.06
    Act Density 0.020%

    No Known Activations