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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сти
    0.22
    ilibrium
    0.22
     supposedly
    0.21
    UAGES
    0.21
    வன்
    0.21
    エラー
    0.21
    riques
    0.21
    하거나
    0.21
     있기
    0.20
    ваем
    0.20
    POSITIVE LOGITS
     dozen
    0.31
     दर्जन
    0.28
     five
    0.26
     dozens
    0.24
     six
    0.23
    十几
    0.22
     आठ
    0.22
     деся
    0.22
     cinco
    0.21
     four
    0.21
    Act Density 0.123%

    No Known Activations