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

    Neuronpedia

    INDEX
    Explanations

    gene or model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    社会
    0.68
    سال
    0.63
     народного
    0.63
    cję
    0.63
     동안
    0.59
     педагоги
    0.59
     সমাজ
    0.58
    ពេល
    0.58
    макра
    0.58
    dengan
    0.58
    POSITIVE LOGITS
     names
    0.78
     pickups
    0.75
     CPUs
    0.75
     cartridges
    0.70
     albums
    0.68
     puppies
    0.68
     syrups
    0.68
     discs
    0.67
     couplings
    0.67
     autographs
    0.67
    Act Density 0.005%

    No Known Activations