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

    Neuronpedia

    INDEX
    Explanations

    film and media contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    el
    1.53
    an
    1.52
    b
    1.45
    er
    1.43
    es
    1.38
    le
    1.38
    i
    1.34
    ed
    1.34
    d
    1.30
    ли
    1.27
    POSITIVE LOGITS
    شك
    1.16
     a
    1.02
    },
    1.02
     فيلم
    0.98
     architekt
    0.98
    P
    0.97
     amelyek
    0.96
    ية
    0.95
    يتها
    0.92
    ائي
    0.90
    Act Density 0.006%

    No Known Activations