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

    Neuronpedia

    INDEX
    Explanations

    creative text formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    郘
    0.45
    totalPages
    0.41
    ರೀ
    0.41
    悝
    0.40
    𝘿
    0.39
     Владими
    0.38
     제곱
    0.38
     நூற்றாண்டின்
    0.38
     parenchyma
    0.37
     டிகிரி
    0.37
    POSITIVE LOGITS
     ad
    0.47
    인가
    0.42
    /
    0.41
    :
    0.39
     وع
    0.38
    anya
    0.37
    ::
    0.37
    AD
    0.36
    uhan
    0.36
    ;
    0.36
    Act Density 0.037%

    No Known Activations