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

    Neuronpedia

    INDEX
    Explanations

    secret word or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maî
    0.80
     bail
    0.70
     desain
    0.67
    ↵
    0.66
     već
    0.65
    ANT
    0.64
     魔
    0.64
    蛲
    0.64
     grou
    0.63
    َرْ
    0.63
    POSITIVE LOGITS
    п
    0.95
    நபியே
    0.88
    ക്രമ
    0.87
    ی
    0.87
    いきます
    0.82
    imhe
    0.82
    いった
    0.82
    сны
    0.80
    б
    0.80
     cardiomyocytes
    0.79
    Act Density 0.000%

    No Known Activations