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

    Neuronpedia

    INDEX
    Explanations

    encoding and decoding text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ovip
    0.43
    PERATURE
    0.42
     requer
    0.41
     querc
    0.40
    Celula
    0.39
    fé
    0.39
    ःख
    0.39
     vies
    0.38
    requis
    0.38
     veulent
    0.38
    POSITIVE LOGITS
     আরও
    0.47
     MORE
    0.45
     more
    0.42
     आणखी
    0.41
     ALL
    0.41
     All
    0.40
    MORE
    0.40
     আরো
    0.39
    ALL
    0.38
     Trends
    0.38
    Act Density 0.000%

    No Known Activations