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

    Neuronpedia

    INDEX
    Explanations

    Code/Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Quran
    -0.06
    arlar
    -0.06
     ako
    -0.06
    olynomial
    -0.06
     aides
    -0.06
    tatus
    -0.06
    ектор
    -0.06
     arch
    -0.06
     budget
    -0.06
     [];
↵
    -0.06
    POSITIVE LOGITS
    角
    0.06
    	tv
    0.06
     một
    0.06
     نج
    0.06
    RESULT
    0.06
    ��
    0.06
     أغسطس
    0.06
    哥
    0.06
     巴
    0.06
    _Param
    0.06
    Act Density 0.000%

    No Known Activations