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

    Neuronpedia

    INDEX
    Explanations

    legal acts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    зации
    -0.07
    らく
    -0.07
    امل
    -0.07
    structuring
    -0.07
     creepy
    -0.06
    ьют
    -0.06
     imports
    -0.06
    isher
    -0.06
    lor
    -0.06
    ÇÃO
    -0.06
    POSITIVE LOGITS
     Πλη
    0.07
    Exclude
    0.07
     Polish
    0.07
    _MORE
    0.06
     Entr
    0.06
     Βασ
    0.06
     Wak
    0.06
     όμως
    0.06
     Tweets
    0.06
     tabel
    0.06
    Act Density 0.010%

    No Known Activations