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

    Neuronpedia

    INDEX
    Explanations

    place name suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     чёр
    -1.71
     pases
    -1.52
     разнообраз
    -1.50
     gavetas
    -1.46
     родствен
    -1.43
    了两
    -1.43
    ABAD
    -1.42
    걍
    -1.41
    yı
    -1.41
    bär
    -1.41
    POSITIVE LOGITS
    :
    1.95
     (
    1.87
     -
    1.80
    ;
    1.72
    ，
    1.70
     by
    1.64
     //
    1.63
    )
    1.61
    ::
    1.59
    (
    1.59
    Act Density 0.253%

    No Known Activations