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

    Neuronpedia

    INDEX
    Explanations

    text with emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Recipes
    1.52
     Coins
    1.43
     Bees
    1.34
     Bikes
    1.33
     Landscapes
    1.31
     Rewards
    1.31
     Genres
    1.30
     Technologies
    1.30
     Miners
    1.30
     Releases
    1.30
    POSITIVE LOGITS
    decision
    1.76
    re
    1.73
    return
    1.72
    pre
    1.71
    cl
    1.70
    pro
    1.69
    impact
    1.69
    energy
    1.69
    un
    1.68
    public
    1.68
    Act Density 0.852%

    No Known Activations