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

    Neuronpedia

    INDEX
    Explanations

    rating and rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neoprene
    0.44
     leopards
    0.44
     flamingo
    0.42
    зву
    0.42
     onyx
    0.42
    ים
    0.41
     marinated
    0.41
     Akar
    0.41
     railway
    0.41
    い
    0.40
    POSITIVE LOGITS
    ings
    0.55
    rated
    0.52
    ert
    0.50
    cline
    0.48
     Rated
    0.47
     rated
    0.46
    cliffe
    0.45
    Ratings
    0.45
     Rat
    0.44
    cales
    0.44
    Act Density 0.007%

    No Known Activations