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

    Neuronpedia

    INDEX
    Explanations

    adjective noun pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dataset
    1.13
    dataset
    0.93
     situatie
    0.91
     conundrum
    0.91
     situation
    0.88
     codebase
    0.88
     storyline
    0.87
     stylesheet
    0.87
     phénomène
    0.86
     differentiator
    0.85
    POSITIVE LOGITS
     credentials
    1.14
     odds
    1.05
     vibes
    1.05
     proportions
    0.93
    credentials
    0.90
     shoes
    0.88
     chops
    0.87
     auspices
    0.86
     footage
    0.86
     digits
    0.85
    Act Density 0.455%

    No Known Activations