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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts and their contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     methods
    0.90
     versions
    0.83
     restantes
    0.83
     elements
    0.82
     activities
    0.82
     gateways
    0.81
     pillars
    0.80
    ները
    0.80
     images
    0.79
     সদস্যদের
    0.77
    POSITIVE LOGITS
    和一个
    1.27
     codebase
    0.92
     dataset
    0.90
     parser
    0.87
     debugger
    0.85
    යක්
    0.80
    someone
    0.77
     scraper
    0.76
    пробу
    0.75
     Unlike
    0.74
    Act Density 1.282%

    No Known Activations