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

    Neuronpedia

    INDEX
    Explanations

    conjug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    飓
    -0.07
    쩼
    -0.07
    マー
    -0.07
     ure
    -0.07
     المر
    -0.07
    (bg
    -0.07
    點
    -0.07
    禀
    -0.06
     dri
    -0.06
    ◞
    -0.06
    POSITIVE LOGITS
    ories
    0.07
    命令
    0.07
    =L
    0.07
    (Local
    0.07
     They
    0.06
    chmod
    0.06
     geschichten
    0.06
     Maybe
    0.06
    riteln
    0.06
     sorry
    0.06
    Act Density 0.032%

    No Known Activations