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

    Neuronpedia

    INDEX
    Explanations

    proteases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fusion
    -0.07
    .getNumber
    -0.07
     Consumption
    -0.07
     Truly
    -0.07
     دری
    -0.07
     Sutton
    -0.06
    .reward
    -0.06
     tük
    -0.06
    ेदन
    -0.06
    torrent
    -0.06
    POSITIVE LOGITS
     PartialView
    0.06
     HOW
    0.06
     prostate
    0.06
     Removing
    0.06
    CAPE
    0.06
     pouze
    0.06
     Οι
    0.06
    (route
    0.06
     Appendix
    0.06
    ASTE
    0.06
    Act Density 0.001%

    No Known Activations