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

    Neuronpedia

    INDEX
    Explanations

    grid column spanning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一个个
    0.42
    只有一个
    0.39
    が通販できます
    0.38
     nen
    0.37
     satu
    0.37
     activos
    0.37
     Compat
    0.36
     Silhouette
    0.36
     tin
    0.36
     ziem
    0.36
    POSITIVE LOGITS
     spanning
    0.68
    colspan
    0.66
    spanning
    0.63
     span
    0.59
    Span
    0.59
     spanned
    0.59
     spans
    0.56
    SPAN
    0.56
     объеди
    0.56
     columnspan
    0.52
    Act Density 0.001%

    No Known Activations