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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ク
    -0.07
    スク
    -0.07
     Ng
    -0.07
     Yug
    -0.07
    ulp
    -0.07
    結
    -0.07
     Kul
    -0.07
     hesitation
    -0.07
    ์ก
    -0.07
    ו�
    -0.07
    POSITIVE LOGITS
      ↵
    0.12
      ↵↵
    0.08
    ERA
    0.08
        ↵↵↵
    0.08
    559
    0.07
    erry
    0.07
     dziew
    0.07
    shot
    0.07
         ↵
    0.07
    779
    0.07
    Act Density 0.018%

    No Known Activations