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

    Neuronpedia

    INDEX
    Explanations

    similar to X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     same
    0.61
    same
    0.55
     selben
    0.49
     საერთ
    0.47
    同一个
    0.47
     동일
    0.46
     അതേ
    0.44
     samme
    0.44
     mesmas
    0.44
    ौनक
    0.44
    POSITIVE LOGITS
    ities
    0.86
    Similar
    0.71
    类似
    0.64
     Similar
    0.63
     similar
    0.59
    ily
    0.59
    類似
    0.57
     подобные
    0.55
     similares
    0.54
    类似的
    0.54
    Act Density 0.004%

    No Known Activations