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

    Neuronpedia

    INDEX
    Explanations

    From the following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     twitter
    0.53
    Twitter
    0.50
    twitter
    0.48
     ट्विटर
    0.46
     tweeted
    0.46
    Luke
    0.44
    ओम
    0.44
    čnost
    0.43
    Spo
    0.42
     pneus
    0.41
    POSITIVE LOGITS
     (<
    0.37
     (%)
    0.36
     (?,
    0.36
     BCC
    0.35
    崭
    0.34
    ئن
    0.33
     enclose
    0.33
     முன்ன
    0.33
     sembl
    0.33
     tread
    0.33
    Act Density 0.000%

    No Known Activations