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

    Neuronpedia

    INDEX
    Explanations

    red followed by context specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Augmented
    0.51
     Adequate
    0.45
    ([...
    0.42
    ברו
    0.42
    จร
    0.41
     Auger
    0.39
    කාශ
    0.39
     Esa
    0.39
    เปอร์
    0.39
     Appellate
    0.38
    POSITIVE LOGITS
     red
    1.09
    red
    1.05
    Red
    1.03
    红
    0.99
    RED
    0.94
    紅
    0.93
     Red
    0.91
     레드
    0.90
     レッド
    0.89
     красный
    0.89
    Act Density 0.068%

    No Known Activations