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

    Neuronpedia

    INDEX
    Explanations

    of the same kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    advantages
    0.48
    োদ্ধ
    0.47
    said
    0.45
     म्हणाले
    0.43
    rax
    0.42
     zodat
    0.42
     כדי
    0.42
    以便
    0.42
     Чтобы
    0.41
    Чтобы
    0.41
    POSITIVE LOGITS
     similarly
    0.71
     ähnlich
    0.58
     مشابه
    0.57
     ebenfalls
    0.55
     similar
    0.54
     celebración
    0.54
     celebra
    0.52
     especial
    0.51
     ähn
    0.51
     nella
    0.50
    Act Density 0.003%

    No Known Activations