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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pyr
    0.39
     gun
    0.38
    피
    0.38
     모습
    0.37
     clinicians
    0.36
    lamide
    0.36
     법
    0.35
    rombin
    0.35
     enemies
    0.35
    lovers
    0.35
    POSITIVE LOGITS
     argent
    0.43
    راض
    0.40
    argent
    0.39
     raio
    0.38
     gastronom
    0.38
     utilizzo
    0.37
     autobi
    0.36
    鑽
    0.36
     সিল
    0.36
     لط
    0.36
    Act Density 0.003%

    No Known Activations