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

    Neuronpedia

    INDEX
    Explanations

    ref, Watch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    祧
    -0.07
    ⓖ
    -0.07
     oversized
    -0.07
     stupid
    -0.07
    璀
    -0.06
    Eric
    -0.06
    經驗
    -0.06
    ╙
    -0.06
     Numeric
    -0.06
     During
    -0.06
    POSITIVE LOGITS
     추진
    0.07
    уют
    0.07
    磐
    0.07
    .conv
    0.07
    工作岗位
    0.07
     bb
    0.07
     nuestra
    0.07
    网店
    0.06
     Folder
    0.06
    绊
    0.06
    Act Density 0.000%

    No Known Activations