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

    Neuronpedia

    INDEX
    Explanations

    code gradient change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    长
    0.57
     Kubo
    0.54
    庾
    0.52
     Pediatric
    0.48
     Dairy
    0.48
     长
    0.47
     Weekly
    0.47
    我们
    0.47
     Honey
    0.47
    長
    0.46
    POSITIVE LOGITS
    time
    0.53
     watchlist
    0.50
     gene
    0.48
    pt
    0.47
    ldes
    0.47
    ul
    0.46
      
    0.46
     time
    0.46
    uk
    0.45
     blazer
    0.44
    Act Density 0.000%

    No Known Activations