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

    Neuronpedia

    INDEX
    Explanations

    location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    هدف
    -0.06
    [-
    -0.06
     emulator
    -0.06
    Pts
    -0.06
     firmware
    -0.06
     gearing
    -0.05
    ันด
    -0.05
     signup
    -0.05
    (interp
    -0.05
     людини
    -0.05
    POSITIVE LOGITS
    050
    0.08
     Bec
    0.07
     Hok
    0.07
    ται
    0.07
     Alexand
    0.07
    createClass
    0.07
    ObjectContext
    0.07
     lesbi
    0.07
     removeObject
    0.07
     clase
    0.07
    Act Density 0.001%

    No Known Activations