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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    法制
    -0.08
    셑
    -0.07
    -storage
    -0.07
    生态文明
    -0.07
     Oz
    -0.07
     equations
    -0.07
    ī
    -0.07
     prepared
    -0.07
     file
    -0.07
    美妙
    -0.06
    POSITIVE LOGITS
     Moder
    0.07
    一致性
    0.07
    🚩
    0.07
    ocular
    0.06
    Exp
    0.06
    UTILITY
    0.06
    untary
    0.06
    _modify
    0.06
     мягк
    0.06
    持续推进
    0.06
    Act Density 0.004%

    No Known Activations