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

    Neuronpedia

    INDEX
    Explanations

    common C# code namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amounts
    0.87
     страна
    0.85
     ilość
    0.85
    ånd
    0.84
    NAD
    0.82
    힘
    0.79
    abs
    0.79
    เบียน
    0.78
     наиболь
    0.78
     chứa
    0.77
    POSITIVE LOGITS
     Equestrian
    0.85
     cycling
    0.80
    ServiceModel
    0.80
     herald
    0.80
    الت
    0.77
     biking
    0.77
     lyric
    0.76
     spectroscopy
    0.75
     beryllium
    0.75
     broadband
    0.74
    Act Density 0.006%

    No Known Activations