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

    Neuronpedia

    INDEX
    Explanations

    frequency of words and subword tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    运维
    0.54
    ਲਾਂ
    0.52
    Pension
    0.52
    鉚
    0.48
     fiancé
    0.48
    💑
    0.47
     Geschä
    0.47
     सीआरपीएफ
    0.47
     వాహ
    0.47
     fiancée
    0.47
    POSITIVE LOGITS
     lexical
    1.08
     linguistic
    1.06
     linguistics
    1.06
     vocabulary
    1.05
     Vocabulary
    1.05
    词
    1.03
     Linguistics
    1.01
     Linguistic
    1.01
     Dictionary
    0.99
     dictionary
    0.97
    Act Density 0.342%

    No Known Activations