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

    Neuronpedia

    INDEX
    Explanations

    edition preview

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     andro
    0.43
     débar
    0.42
     कहला
    0.38
    тли
    0.38
    嵇
    0.37
     corticosteroids
    0.36
    నకు
    0.36
     مواد
    0.35
    efeuille
    0.35
     antiviral
    0.35
    POSITIVE LOGITS
    DJ
    0.38
     कॉलेज
    0.38
    insp
    0.37
     highlighted
    0.36
     JUST
    0.35
     Jus
    0.35
     Pans
    0.35
    ನೀ
    0.34
    Pan
    0.34
     isAdmin
    0.34
    Act Density 0.002%

    No Known Activations