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

    Neuronpedia

    INDEX
    Explanations

    urls and shortened links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rasp
    0.37
     পুরোনো
    0.36
     Auff
    0.35
     bhavanti
    0.35
     koment
    0.35
     Vind
    0.35
    Gover
    0.34
     Obtained
    0.34
     Sib
    0.34
     புற
    0.34
    POSITIVE LOGITS
     shorten
    0.82
     shortened
    0.81
     shortening
    0.79
    link
    0.69
     link
    0.68
     Link
    0.65
     URL
    0.65
    url
    0.64
    URL
    0.63
    Link
    0.62
    Act Density 0.051%

    No Known Activations