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

    Neuronpedia

    INDEX
    Explanations

    community engagement and outreach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obsess
    0.63
     obses
    0.61
     massive
    0.58
     explicitly
    0.57
     massively
    0.57
     debug
    0.57
     algorithms
    0.55
     architectures
    0.54
     obsession
    0.54
     trillions
    0.54
    POSITIVE LOGITS
    community
    1.00
    Community
    0.98
     outreach
    0.95
     Outreach
    0.92
     सामुदायिक
    0.90
     community
    0.90
     Community
    0.89
     COMMUNITY
    0.87
     initiatives
    0.86
    社區
    0.85
    Act Density 0.004%

    No Known Activations