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

    Neuronpedia

    INDEX
    Explanations

    Citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     территории
    -0.07
    ｢
    -0.07
    懈
    -0.06
    之际
    -0.06
    华侨
    -0.06
    渼
    -0.06
    ricing
    -0.06
    erv
    -0.06
     вопросы
    -0.06
    但对于
    -0.06
    POSITIVE LOGITS
    FULL
    0.07
    ,*
    0.07
     какие
    0.07
     draggable
    0.06
    صنع
    0.06
    REG
    0.06
    Chunks
    0.06
     Department
    0.06
     autocomplete
    0.06
    cached
    0.06
    Act Density 0.002%

    No Known Activations