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

    Neuronpedia

    INDEX
    Explanations

    job data keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     durations
    0.84
     Locations
    0.79
    товано
    0.74
     contexts
    0.74
    错误的
    0.74
     suffixes
    0.73
    <unused217>
    0.71
     ит
    0.71
    माटर
    0.70
     පුද්ග
    0.68
    POSITIVE LOGITS
     aka
    0.74
     seperti
    0.69
     eponymous
    0.64
     como
    0.62
     like
    0.61
     bood
    0.60
    ={()
    0.59
     terhadap
    0.58
     berfungsi
    0.57
     dedi
    0.57
    Act Density 0.842%

    No Known Activations