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

    Neuronpedia

    INDEX
    Explanations

    hollywood movies and industry figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.94
    ac
    0.85
    as
    0.74
    ي
    0.74
    П
    0.72
    lL
    0.71
    id
    0.70
    au
    0.70
    ol
    0.69
    atr
    0.68
    POSITIVE LOGITS
    ти
    0.84
     movies
    0.73
     uncanny
    0.64
    ,’
    0.58
     Movies
    0.57
    ↵
    0.56
     Hollywood
    0.55
     фильма
    0.54
    </h2>
    0.52
     ยก
    0.52
    Act Density 0.002%

    No Known Activations