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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิท
    -0.07
     defenders
    -0.07
    틀
    -0.06
     леж
    -0.06
    İS
    -0.06
     tiếp
    -0.06
     sands
    -0.06
    )(_
    -0.06
    римін
    -0.06
     два
    -0.06
    POSITIVE LOGITS
     suggests
    0.06
    HOW
    0.06
     aby
    0.06
     est
    0.06
    联盟
    0.06
     ontvangst
    0.06
    alloc
    0.06
     sou
    0.06
     Claims
    0.06
    ishops
    0.06
    Act Density 0.002%

    No Known Activations