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

    Neuronpedia

    INDEX
    Explanations

    text refinement and simplification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (((
    0.96
     (
    0.95
     భారతదేశ
    0.89
     (!)
    0.89
    ↵↵
    0.88
     (*
    0.85
     খ্রিস্ট
    0.84
    ภาษ
    0.84
    所有
    0.83
     (+
    0.83
    POSITIVE LOGITS
     Grower
    1.62
     Smile
    1.60
     Tasty
    1.57
     Beauty
    1.56
     Graffiti
    1.55
     Bottle
    1.54
     Flower
    1.53
     Happy
    1.53
     Ideen
    1.52
     Lounge
    1.51
    Act Density 0.406%

    No Known Activations