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

    Neuronpedia

    INDEX
    Explanations

    online reviews and ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    calculations
    0.48
    Tracing
    0.45
     conceptually
    0.45
     sécr
    0.44
     Calculations
    0.43
     symbolically
    0.43
     calculations
    0.43
    ლება
    0.42
    Visualization
    0.42
    definitions
    0.40
    POSITIVE LOGITS
     reviews
    2.06
     Reviews
    1.84
    Reviews
    1.77
    reviews
    1.77
     отзывы
    1.74
     ratings
    1.57
     review
    1.55
     reviewers
    1.51
     reseñas
    1.51
     rating
    1.49
    Act Density 0.034%

    No Known Activations