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

    Neuronpedia

    INDEX
    Explanations

    Context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    꿩
    -0.07
     spoiler
    -0.07
    icap
    -0.07
     Piper
    -0.06
    灰色
    -0.06
     какой
    -0.06
    죔
    -0.06
    ❪
    -0.06
    Properties
    -0.06
    Ace
    -0.06
    POSITIVE LOGITS
    大地
    0.08
     登
    0.07
    ('.
    0.07
     walkers
    0.07
     tích
    0.07
     child
    0.07
    -du
    0.07
     "-",
    0.07
    河流
    0.07
     Thou
    0.07
    Act Density 0.002%

    No Known Activations