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

    Neuronpedia

    INDEX
    Explanations

    onion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     padd
    -0.07
    审议
    -0.07
    _struct
    -0.07
    鳔
    -0.07
    改革发展
    -0.07
    驽
    -0.07
    汲
    -0.06
    三大
    -0.06
     cade
    -0.06
    (insert
    -0.06
    POSITIVE LOGITS
     onion
    0.08
     Exception
    0.08
    общи
    0.07
    шен
    0.07
     Metropolitan
    0.07
    Ni
    0.07
     Env
    0.07
     theories
    0.07
    .fixed
    0.07
     onions
    0.07
    Act Density 0.002%

    No Known Activations