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

    Neuronpedia

    INDEX
    Explanations

    attributes and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     finanzi
    0.57
     việc
    0.56
    βολ
    0.54
    كشن
    0.52
    ك
    0.52
     Tackle
    0.52
     Tahun
    0.51
     provoz
    0.51
     cabaret
    0.50
    ف
    0.50
    POSITIVE LOGITS
     attributes
    1.26
     characteristics
    1.24
    characteristics
    1.19
     qualities
    1.14
     atributos
    1.13
     Attributes
    1.08
    特性
    1.05
     Characteristics
    1.05
    attributes
    1.03
     характеристи
    1.02
    Act Density 0.110%

    No Known Activations