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

    Neuronpedia

    INDEX
    Explanations

    injected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    生产总值
    -0.07
    瑰
    -0.07
     extras
    -0.07
     stared
    -0.07
    全景
    -0.07
     greeting
    -0.07
    .btnExit
    -0.07
     hath
    -0.07
    灈
    -0.07
    минист
    -0.07
    POSITIVE LOGITS
     %↵↵
    0.08
    inds
    0.07
    represent
    0.07
    挨
    0.07
    'am
    0.07
    arse
    0.07
    sek
    0.07
    _contract
    0.07
    αι
    0.07
    最初
    0.07
    Act Density 0.002%

    No Known Activations