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

    Neuronpedia

    INDEX
    Explanations

    explaining phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    loyd
    0.45
     Implementation
    0.45
     Coord
    0.45
    blit
    0.41
     implementation
    0.41
     reminders
    0.39
     creditors
    0.39
     Awareness
    0.39
    convex
    0.38
     Kanban
    0.38
    POSITIVE LOGITS
     phenomena
    0.88
     phenomenon
    0.76
    現象
    0.75
     fenómenos
    0.75
     fenomeni
    0.75
     phénomène
    0.74
     fenô
    0.74
     phénomènes
    0.73
     fenómeno
    0.68
     поведения
    0.66
    Act Density 0.253%

    No Known Activations