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

    Neuronpedia

    INDEX
    Explanations

    workload

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bathrooms
    -0.07
     lắp
    -0.07
    auga
    -0.07
    buy
    -0.07
    民主
    -0.06
     oxy
    -0.06
     coupons
    -0.06
     Keith
    -0.06
     страх
    -0.06
    addField
    -0.06
    POSITIVE LOGITS
     workload
    0.16
     takes
    0.07
    loads
    0.07
    ---@
    0.07
    лож
    0.07
    Throughout
    0.06
     सम
    0.06
    Workspace
    0.06
     =>{↵
    0.06
    cur
    0.06
    Act Density 0.001%

    No Known Activations