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

    Neuronpedia

    INDEX
    Explanations

    PCIe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     task
    -0.07
     costs
    -0.06
    aud
    -0.06
    studio
    -0.06
    imate
    -0.06
     north
    -0.06
     Numbers
    -0.06
     rewards
    -0.06
     новых
    -0.06
    habi
    -0.06
    POSITIVE LOGITS
     PCIe
    0.12
     isEnabled
    0.07
     завер
    0.06
     calming
    0.06
    หลด
    0.06
     भगव
    0.06
     pParent
    0.06
     фер
    0.06
     peter
    0.06
     ;;^
    0.06
    Act Density 0.001%

    No Known Activations