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

    Neuronpedia

    INDEX
    Explanations

    tract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DEPTH
    -0.08
    herits
    -0.07
    _wheel
    -0.06
    (answer
    -0.06
     eyel
    -0.06
     Metadata
    -0.06
     dziew
    -0.06
     Restore
    -0.06
     spre
    -0.06
     윤
    -0.06
    POSITIVE LOGITS
     trúc
    0.06
     lake
    0.06
    (real
    0.06
     descriptions
    0.06
     attempted
    0.06
     UnityEngine
    0.06
     常
    0.06
    xing
    0.06
    ड़
    0.06
     simmer
    0.06
    Act Density 0.007%

    No Known Activations