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

    Neuronpedia

    INDEX
    Explanations

    introduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    澳大
    -0.27
    olithic
    -0.26
    Rom
    -0.26
    ç¬Ķ
    -0.26
    ä¸įæĿ¥
    -0.26
     dog
    -0.25
    yte
    -0.25
    ButtonDown
    -0.24
    osl
    -0.24
    åĨ¼
    -0.24
    POSITIVE LOGITS
    轨
    0.28
    è¡Ĺ
    0.27
    -cn
    0.27
    æĽĿåħī
    0.26
    rü
    0.26
    hips
    0.25
    ETF
    0.25
    åĴĢ
    0.25
    oup
    0.25
    æĪIJåĬŁçİĩ
    0.25
    Act Density 1.132%

    No Known Activations