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

    Neuronpedia

    INDEX
    Explanations

    URL paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     te
    0.94
    -
    0.92
     co
    0.88
     an
    0.87
     back
    0.86
     one
    0.85
     at
    0.84
     farm
    0.84
     bird
    0.84
     sent
    0.83
    POSITIVE LOGITS
    Articles
    1.59
    topics
    1.47
    produkte
    1.44
    categories
    1.41
    articles
    1.39
    articolo
    1.36
    article
    1.36
    categorie
    1.35
     ARTICLES
    1.35
    producto
    1.34
    Act Density 0.274%

    No Known Activations