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

    Neuronpedia

    INDEX
    Explanations

    daily, weekly, hourly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    だけで
    0.70
     tired
    0.69
     Kult
    0.69
     kapasitas
    0.69
     দাড়
    0.67
    itio
    0.67
     تنت
    0.66
     lowered
    0.64
     harboring
    0.63
     falo
    0.62
    POSITIVE LOGITS
    Even
    0.96
     Even
    0.93
     nawet
    0.91
     even
    0.89
     Hourly
    0.88
    EVEN
    0.87
     EVEN
    0.87
     thậm
    0.86
    Weekly
    0.85
    hourly
    0.85
    Act Density 0.000%

    No Known Activations