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

    Neuronpedia

    INDEX
    Explanations

    appreciated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    стью
    -0.08
    急速
    -0.07
    ấu
    -0.07
    bew
    -0.07
    ﴩ
    -0.07
     wc
    -0.07
     לק
    -0.07
     frem
    -0.07
     dex
    -0.07
    bler
    -0.06
    POSITIVE LOGITS
    吳
    0.07
    --------↵
    0.07
     pigs
    0.07
    News
    0.07
     Pearl
    0.07
    吴
    0.07
     ||
    0.06
    時の
    0.06
    𝚝
    0.06
     Andy
    0.06
    Act Density 0.004%

    No Known Activations