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

    Neuronpedia

    INDEX
    Explanations

    question options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ফেস
    0.81
    দীন
    0.76
     ću
    0.74
    酞
    0.73
     honesty
    0.71
     esetben
    0.71
     डिलिव
    0.71
    0.70
     ocasion
    0.70
    یکیشن
    0.70
    POSITIVE LOGITS
    ↵↵
    0.88
     of
    0.71
    ↵
    0.69
     दोगु
    0.66
    of
    0.66
     Viewed
    0.63
    Multiple
    0.58
     among
    0.58
    ibid
    0.58
    ."
    0.57
    Act Density 0.000%

    No Known Activations