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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لك
    -0.07
    犯
    -0.07
    ге
    -0.07
    фе
    -0.07
     spectra
    -0.07
    珙
    -0.07
    随着
    -0.07
    集聚
    -0.07
     grou
    -0.07
     classes
    -0.06
    POSITIVE LOGITS
    ᾏ
    0.07
    USH
    0.07
    (Action
    0.07
     zobow
    0.06
    (fout
    0.06
    民俗
    0.06
    RD
    0.06
    鸿
    0.06
    \Field
    0.06
     accounting
    0.06
    Act Density 0.031%

    No Known Activations