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

    Neuronpedia

    INDEX
    Explanations

    Names/References

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ontvangst
    -0.07
    ILING
    -0.07
    xious
    -0.07
    平均水平
    -0.07
    不僅
    -0.07
    -tests
    -0.07
    翾
    -0.06
    易于
    -0.06
    .Scene
    -0.06
    sts
    -0.06
    POSITIVE LOGITS
    (predicate
    0.07
     Mae
    0.07
    뽑
    0.07
    quo
    0.07
    iros
    0.07
     Poe
    0.07
    虹桥
    0.06
    �
    0.06
    Playable
    0.06
    iversal
    0.06
    Act Density 0.083%

    No Known Activations