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

    Neuronpedia

    INDEX
    Explanations

    room/rooms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drinking
    -0.07
     silicon
    -0.06
    .testing
    -0.06
    SEARCH
    -0.06
     Orchestra
    -0.06
    -cons
    -0.06
    alaxy
    -0.06
    Leader
    -0.06
    ificación
    -0.06
     disappearance
    -0.06
    POSITIVE LOGITS
     rooms
    0.08
     roomId
    0.07
    ="#"
    0.07
    났
    0.06
    ตำแหน
    0.06
    _greater
    0.06
    mid
    0.06
    ey
    0.06
     اتاق
    0.06
     wooded
    0.06
    Act Density 0.007%

    No Known Activations