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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﲇ
    -0.07
    鹾
    -0.07
     citt
    -0.07
     discuss
    -0.07
    提出的
    -0.06
    .original
    -0.06
    柈
    -0.06
    旗
    -0.06
    Definitions
    -0.06
    酃
    -0.06
    POSITIVE LOGITS
    nger
    0.08
    ’↵↵
    0.08
     🙂
    0.07
    .piece
    0.07
     LAS
    0.07
    *</
    0.07
    Replacing
    0.07
    onta
    0.07
     계
    0.07
    行列
    0.07
    Act Density 0.028%

    No Known Activations