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

    Neuronpedia

    INDEX
    Explanations

    code punctuation and verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    科
    0.69
    字符
    0.68
     بالإضافة
    0.68
    を追加
    0.68
    additional
    0.66
     interesante
    0.64
    +,
    0.63
     ಒ
    0.62
     допъл
    0.62
    Spart
    0.62
    POSITIVE LOGITS
     saying
    0.71
     বলিলেন
    0.67
     say
    0.65
    ানির
    0.64
     Analysis
    0.63
    мот
    0.63
    沚
    0.62
    ytics
    0.62
    大多數
    0.61
     said
    0.61
    Act Density 0.287%

    No Known Activations