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

    Neuronpedia

    INDEX
    Explanations

    counties, districts, and prefectures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    -1.66
     هو
    -1.59
    ;
    -1.57
    [
    -1.52
    If
    -1.51
    I
    -1.51
    )
    -1.48
     –
    -1.48
    When
    -1.44
    {
    -1.41
    POSITIVE LOGITS
     you
    1.72
    lapsingToolbar
    1.53
    ⤙
    1.48
    辔
    1.47
    ꔛ
    1.47
     County
    1.45
     إحدى
    1.44
    锨
    1.40
     eerste
    1.40
     которы
    1.40
    Act Density 0.227%

    No Known Activations