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

    Neuronpedia

    INDEX
    Explanations

    Python code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    损坏
    0.46
     будет
    0.45
    যদি
    0.44
    Logical
    0.43
    昰
    0.43
     बॉर्डर
    0.42
    র্পণ
    0.42
     കൂട
    0.42
    边
    0.42
    ologien
    0.41
    POSITIVE LOGITS
     condensed
    0.52
     produt
    0.46
    glasses
    0.44
    filter
    0.43
     göz
    0.43
     tuple
    0.42
     classics
    0.42
     enzymes
    0.42
     eyewear
    0.41
     lenses
    0.41
    Act Density 0.436%

    No Known Activations