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

    Neuronpedia

    INDEX
    Explanations

    composition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resides
    -0.07
    Art
    -0.06
     userid
    -0.06
    чні
    -0.06
     पहच
    -0.06
    card
    -0.06
    -work
    -0.06
     Tenant
    -0.06
    Wolf
    -0.06
    δι
    -0.06
    POSITIVE LOGITS
     tries
    0.07
     obsess
    0.07
    autoplay
    0.07
    ={'
    0.07
     wonderfully
    0.06
    objectManager
    0.06
     bustling
    0.06
     empir
    0.06
     customize
    0.06
     etiqu
    0.06
    Act Density 0.012%

    No Known Activations