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

    Neuronpedia

    INDEX
    Explanations

    rating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pharmacies
    -0.07
     cheeks
    -0.07
     cave
    -0.07
     Shore
    -0.06
     Science
    -0.06
     Venture
    -0.06
     Communities
    -0.06
     Beach
    -0.06
     Transparency
    -0.06
    Ob
    -0.06
    POSITIVE LOGITS
     ratings
    0.09
     rating
    0.09
    _ratings
    0.08
    .tif
    0.08
    ratings
    0.07
    Rating
    0.07
     rated
    0.07
     Armor
    0.07
    rating
    0.07
     Ratings
    0.07
    Act Density 0.010%

    No Known Activations