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

    Neuronpedia

    INDEX
    Explanations

    reading or supplements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     അവസ
    0.43
     publications
    0.43
     crafted
    0.43
    publications
    0.40
    সাম
    0.40
     documentaries
    0.40
     popular
    0.40
     embellished
    0.40
     publiés
    0.40
     published
    0.38
    POSITIVE LOGITS
     photocopying
    0.67
     photocopy
    0.56
     Supplement
    0.52
    Bookmark
    0.48
     అధ్య
    0.46
     заклад
    0.46
     consulting
    0.46
     Consulting
    0.45
     biblioteca
    0.45
     bookmark
    0.44
    Act Density 0.029%

    No Known Activations