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

    Neuronpedia

    INDEX
    Explanations

    desk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     solves
    -0.07
     poem
    -0.07
     land
    -0.06
     сво
    -0.06
     เขต
    -0.06
     Bunu
    -0.06
    ham
    -0.06
     Coke
    -0.06
    -driver
    -0.06
    .country
    -0.06
    POSITIVE LOGITS
     Desk
    0.18
    Desk
    0.16
    desk
    0.16
     desk
    0.11
    esk
    0.09
     Pulse
    0.07
     desks
    0.07
    .disk
    0.07
    bere
    0.07
    Disk
    0.07
    Act Density 0.001%

    No Known Activations