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

    Neuronpedia

    INDEX
    Explanations

    Plagiarism/repeating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -themed
    -0.07
    教授
    -0.07
     Fireplace
    -0.06
    _acquire
    -0.06
     lottery
    -0.06
    ої
    -0.06
     каф
    -0.06
    背
    -0.06
     президент
    -0.06
     Hogwarts
    -0.06
    POSITIVE LOGITS
     сос
    0.07
     Secondly
    0.07
    错误
    0.06
     CT
    0.06
    一级
    0.06
     Michele
    0.06
    tiny
    0.06
    -img
    0.06
     몰
    0.06
    行
    0.06
    Act Density 0.013%

    No Known Activations