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

    Neuronpedia

    INDEX
    Explanations

    Sales

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stripe
    -0.06
    (name
    -0.06
    BOVE
    -0.06
    /Z
    -0.06
     ندارد
    -0.05
    itizen
    -0.05
     iron
    -0.05
    .Directory
    -0.05
     бач
    -0.05
    TPL
    -0.05
    POSITIVE LOGITS
     концеп
    0.07
    нося
    0.07
    ？」↵↵
    0.07
     intercept
    0.07
    datatable
    0.07
     setBackgroundImage
    0.06
    uju
    0.06
    conom
    0.06
    elan
    0.06
     forensic
    0.06
    Act Density 0.041%

    No Known Activations