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

    Neuronpedia

    INDEX
    Explanations

    Cor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kết
    -0.06
    (/[
    -0.06
     Seeing
    -0.06
     hóa
    -0.06
     Ling
    -0.06
    站在
    -0.06
     Personal
    -0.06
    CRY
    -0.06
    ’am
    -0.06
     vind
    -0.06
    POSITIVE LOGITS
     Phillip
    0.07
     ＞
    0.06
    Bin
    0.06
    科技有限公司
    0.06
     Railroad
    0.06
     برنامه
    0.06
    _SPELL
    0.06
    Gar
    0.06
     signature
    0.06
    ason
    0.06
    Act Density 0.057%

    No Known Activations