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

    Neuronpedia

    INDEX
    Explanations

    trends and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Environment
    0.82
    Ди
    0.79
    {
    0.78
    Cyber
    0.77
    Coord
    0.76
    Gaia
    0.75
    Integr
    0.75
    Mia
    0.74
     Environment
    0.73
     Seag
    0.73
    POSITIVE LOGITS
    agogues
    0.88
    alerts
    0.80
     dudas
    0.78
     tendencias
    0.76
    үкт
    0.75
    िवर्स
    0.75
     diameters
    0.74
    bed
    0.73
    ాం
    0.72
     clashes
    0.72
    Act Density 0.003%

    No Known Activations