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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    퍼
    -0.07
     NO
    -0.06
     WE
    -0.06
    \
    -0.06
    一個
    -0.06
     hung
    -0.06
    .txt
    -0.06
     smelled
    -0.06
     diren
    -0.06
     Род
    -0.06
    POSITIVE LOGITS
    ilinx
    0.07
    Force
    0.07
    ights
    0.07
    街道
    0.06
     سازمان
    0.06
    _Set
    0.06
    hil
    0.06
    โครงการ
    0.06
    _drv
    0.06
     Ashley
    0.06
    Act Density 0.190%

    No Known Activations