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

    Neuronpedia

    INDEX
    Explanations

    -based

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Academy
    -0.07
    城市
    -0.06
     Week
    -0.06
     Buzz
    -0.06
    鋼
    -0.06
     penalty
    -0.06
     cell
    -0.06
     monster
    -0.06
     carbonate
    -0.06
     tiền
    -0.06
    POSITIVE LOGITS
     sophisticated
    0.07
    _dat
    0.07
     während
    0.06
    uesta
    0.06
    يه
    0.06
    Remote
    0.06
    الت
    0.06
    ьми
    0.06
    modo
    0.06
    :
↵
    0.06
    Act Density 0.006%

    No Known Activations