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

    Neuronpedia

    INDEX
    Explanations

    mathematics/statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .feed
    -0.07
    usr
    -0.07
     Twin
    -0.07
     Seasons
    -0.06
     grinned
    -0.06
    .password
    -0.06
     Blur
    -0.06
     Ön
    -0.06
    들도
    -0.06
     potassium
    -0.06
    POSITIVE LOGITS
    éné
    0.07
    +S
    0.07
    GBK
    0.06
    市場
    0.06
    από
    0.06
     saddened
    0.06
     Blackburn
    0.06
     Weber
    0.06
     ED
    0.06
    SPATH
    0.06
    Act Density 0.116%

    No Known Activations