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

    Neuronpedia

    INDEX
    Explanations

    royal titles and estates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     साथी
    0.75
     Xuan
    0.73
     शिक्षक
    0.71
     precedenti
    0.69
     子供
    0.68
     dersimizde
    0.68
     ene
    0.67
     轻
    0.67
     ⏮
    0.67
     நாளில்
    0.66
    POSITIVE LOGITS
     of
    0.81
    На
    0.71
    let
    0.67
    Ка
    0.66
    class
    0.63
    ’
    0.63
    kingdom
    0.62
    of
    0.61
    Он
    0.61
    Согласно
    0.61
    Act Density 0.022%

    No Known Activations