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

    Neuronpedia

    INDEX
    Explanations

    load balancer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    smöglichkeiten
    1.56
     amenities
    1.50
     competencies
    1.49
     KPIs
    1.48
     aspects
    1.46
     GPUs
    1.38
     subsidies
    1.38
     benchmarks
    1.38
     उपकरणों
    1.36
     omissions
    1.36
    POSITIVE LOGITS
    和一个
    1.45
     instance
    1.01
     piece
    1.00
    instance
    0.95
     contender
    0.91
     sampler
    0.91
     item
    0.91
     entity
    0.89
     molecule
    0.87
    constructor
    0.85
    Act Density 1.431%

    No Known Activations