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

    Neuronpedia

    INDEX
    Explanations

    greater than or equal to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ভিন্ন
    0.83
    different
    0.80
     ruch
    0.75
     Different
    0.74
    不同的
    0.74
     разных
    0.73
     different
    0.73
     diferentes
    0.72
     distintas
    0.70
     বলে
    0.70
    POSITIVE LOGITS
    >≥</
    1.56
     >=
    1.54
     <=
    1.50
    )>=
    1.46
    >≤</
    1.45
    geq
    1.45
    1.43
    leq
    1.43
     ≥
    1.41
     ≤
    1.40
    Act Density 0.245%

    No Known Activations