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

    Neuronpedia

    INDEX
    Explanations

    exception handling `e:`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trọng
    0.82
     thức
    0.80
     ভ
    0.76
     কার
    0.75
    CTIONS
    0.75
    براین
    0.74
    യുടെ
    0.74
     hôm
    0.73
     thực
    0.73
     эк
    0.73
    POSITIVE LOGITS
    Не
    1.05
    en
    0.98
     localities
    0.96
    jars
    0.96
     elastomers
    0.93
    r
    0.93
    У
    0.93
    Вы
    0.93
     bookcases
    0.92
    enums
    0.91
    Act Density 0.107%

    No Known Activations