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

    Neuronpedia

    INDEX
    Explanations

    vocabulary

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     liné
    0.71
    Indent
    0.69
    Identity
    0.68
    เต
    0.68
     line
    0.68
    خط
    0.66
     LINE
    0.66
    秉
    0.66
    序列
    0.64
    泮
    0.64
    POSITIVE LOGITS
     vocabulary
    1.43
     Vocabulary
    1.33
    Vocabulary
    1.30
     Dictionary
    1.20
     vocab
    1.17
     Thes
    1.16
     dictionary
    1.15
    vocabulary
    1.13
    Dictionary
    1.05
     synonyms
    1.03
    Act Density 0.632%

    No Known Activations