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

    Neuronpedia

    INDEX
    Explanations

    semisimple lie algebra

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BUILD
    -0.07
    ("")↵
    -0.07
    Пр
    -0.07
    сит
    -0.06
     كتب
    -0.06
    以为
    -0.06
    획
    -0.06
    开放
    -0.06
    ifers
    -0.06
    ťan
    -0.06
    POSITIVE LOGITS
     Dedicated
    0.08
     Alle
    0.07
    atism
    0.06
    ]/
    0.06
    )\<
    0.06
     owed
    0.06
     dedicated
    0.06
     قدرت
    0.06
    _PY
    0.06
     elevated
    0.06
    Act Density 0.006%

    No Known Activations