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

    Neuronpedia

    INDEX
    Explanations

    method calls after dot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simonsen
    0.74
     myocytes
    0.66
    dra
    0.66
     pata
    0.63
    ECs
    0.62
    विंद
    0.61
    HRIM
    0.61
     artworks
    0.60
    LEV
    0.60
    Radians
    0.59
    POSITIVE LOGITS
    的力量
    0.58
     Day
    0.58
    น่า
    0.56
     for
    0.55
     Manufacturing
    0.55
     Time
    0.54
     Christmas
    0.54
     Baron
    0.54
     class
    0.54
     Anthony
    0.54
    Act Density 0.030%

    No Known Activations