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

    Neuronpedia

    INDEX
    Explanations

    all modern vehicles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我们会
    0.46
    we
    0.43
    我們會
    0.42
     Microbi
    0.41
    我們要
    0.41
    เรา
    0.41
     మేము
    0.40
     ഞങ്ങൾ
    0.40
    ៩
    0.40
    我们将
    0.40
    POSITIVE LOGITS
     medias
    0.40
    ീക
    0.39
    ದ
    0.38
    ულ
    0.38
    NotDefined
    0.38
     fide
    0.38
     ນ
    0.38
    麺
    0.38
     transferred
    0.38
    Erin
    0.37
    Act Density 0.004%

    No Known Activations