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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >=
    0.63
    leq
    0.62
    >≤</
    0.62
    ძლიათ
    0.59
    と考えて
    0.58
    ustering
    0.57
     crackers
    0.57
    至少
    0.56
    either
    0.56
    反正
    0.55
    POSITIVE LOGITS
     这个
    0.95
    这个
    0.90
    這個
    0.80
     This
    0.78
     這個
    0.78
     هذا
    0.75
     Questo
    0.74
     این
    0.72
     questo
    0.68
     இந்த
    0.67
    Act Density 0.866%

    No Known Activations