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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ultip
    -0.07
    译
    -0.07
    武侠
    -0.06
    ügen
    -0.06
    enefit
    -0.06
     signin
    -0.06
     Hawai
    -0.06
     Calling
    -0.06
     indemn
    -0.06
     średni
    -0.06
    POSITIVE LOGITS
    と言う
    0.07
    稍
    0.07
    �
    0.07
     smooth
    0.07
    频繁
    0.06
    陡
    0.06
    .io
    0.06
     satur
    0.06
     Syrians
    0.06
    ≤
    0.06
    Act Density 0.048%

    No Known Activations