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

    Neuronpedia

    INDEX
    Explanations

    pay dividends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonempty
    0.51
    ﺸ
    0.49
     tabpos
    0.47
     başlı
    0.47
     важ
    0.47
     entrambe
    0.45
     nonEmpty
    0.45
     spoilt
    0.45
    挝
    0.44
    സിൽ
    0.43
    POSITIVE LOGITS
    Estado
    0.48
     p
    0.41
     (
    0.41
     }
    0.41
     (*)
    0.41
     flank
    0.40
     intoxication
    0.39
    InData
    0.39
    (*)
    0.39
    Data
    0.38
    Act Density 0.000%

    No Known Activations