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

    Neuronpedia

    INDEX
    Explanations

    remove noise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     przej
    0.36
     ngoại
    0.36
     infringing
    0.36
     inequities
    0.34
     body
    0.34
     intern
    0.34
    reaching
    0.34
    isActive
    0.34
     جان
    0.34
    াপে
    0.34
    POSITIVE LOGITS
    ophila
    0.45
    柅
    0.43
    IDENTAL
    0.40
    的地
    0.40
    FORMAT
    0.40
     LOCAL
    0.37
    环境变量
    0.37
     were
    0.36
     repeats
    0.36
    下一个
    0.36
    Act Density 0.000%

    No Known Activations