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

    Neuronpedia

    INDEX
    Explanations

    regulators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ıklı
    -0.07
     decrease
    -0.07
     müş
    -0.06
    obook
    -0.06
           ↵
    -0.06
    ului
    -0.06
     invasive
    -0.06
    sah
    -0.06
    扶
    -0.06
     resolution
    -0.06
    POSITIVE LOGITS
     regulators
    0.28
     regulator
    0.25
     watchdog
    0.11
    ulator
    0.10
    ulators
    0.09
     sexually
    0.08
    ULATOR
    0.07
     licensors
    0.07
     spectator
    0.06
    .qq
    0.06
    Act Density 0.002%

    No Known Activations