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

    Neuronpedia

    INDEX
    Explanations

    numbers and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Template
    0.45
    ,
    0.44
    。
    0.43
    S
    0.42
    I
    0.41
    Collection
    0.40
    .
    0.40
    .,
    0.39
     localization
    0.39
    ization
    0.39
    POSITIVE LOGITS
    此同时
    0.50
     giusta
    0.48
     correcto
    0.45
     इश्क
    0.43
    尔多
    0.43
     correctes
    0.43
     அலெக்ஸாண்ட்
    0.43
    歡
    0.43
     montagne
    0.43
    欢
    0.43
    Act Density 0.001%

    No Known Activations