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

    Neuronpedia

    INDEX
    Explanations

    factors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alertController
    -0.07
    จะเป
    -0.07
     Pagination
    -0.07
     cheapest
    -0.07
    -0.07
     watering
    -0.06
    */,
    -0.06
    .Emit
    -0.06
    -0.06
    ολ
    -0.06
    POSITIVE LOGITS
     grant
    0.06
    avior
    0.06
    ivet
    0.06
     conclusions
    0.06
     patter
    0.06
     advise
    0.06
    urally
    0.06
    _wifi
    0.06
    rena
    0.06
    čet
    0.06
    Act Density 0.017%

    No Known Activations