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

    Neuronpedia

    INDEX
    Explanations

    module imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     профи
    0.44
    UIKit
    0.41
     Ваши
    0.38
     टाकी
    0.37
    선의
    0.37
     проверя
    0.37
     작성
    0.36
    કાશ
    0.36
    common
    0.36
    のお
    0.36
    POSITIVE LOGITS
     "@
    0.47
     '@
    0.47
     @
    0.46
     `@
    0.43
    @
    0.40
    "@
    0.39
    '@
    0.38
     ekstrem
    0.38
     ahead
    0.38
     innovative
    0.37
    Act Density 0.002%

    No Known Activations