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

    Neuronpedia

    INDEX
    Explanations

    las

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sonra
    -0.07
     cuối
    -0.07
    Кон
    -0.07
    782
    -0.07
    하여
    -0.07
    172
    -0.07
     その他
    -0.06
     WD
    -0.06
    리그
    -0.06
     اکتبر
    -0.06
    POSITIVE LOGITS
    MAP
    0.07
     fec
    0.06
     bananas
    0.06
     Supplementary
    0.06
    rate
    0.06
     Bethlehem
    0.06
    _tra
    0.06
     financially
    0.06
    rots
    0.06
    Mais
    0.06
    Act Density 0.002%

    No Known Activations