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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wichita
    -0.08
    bbie
    -0.07
    展区
    -0.07
    统计数据
    -0.07
    ccione
    -0.06
    ificação
    -0.06
     Tiffany
    -0.06
    繳
    -0.06
    طا
    -0.06
    牵
    -0.06
    POSITIVE LOGITS
    สาธาร
    0.08
     non
    0.07
    迅猛
    0.07
     Proposal
    0.07
    药师
    0.07
    aea
    0.07
    _em
    0.07
    نت
    0.06
    <Unit
    0.06
    aat
    0.06
    Act Density 0.002%

    No Known Activations