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

    Neuronpedia

    INDEX
    Explanations

    providing examples or links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     married
    0.42
    t
    0.41
     Emperor
    0.41
     Necess
    0.40
     aand
    0.40
     covers
    0.39
     cover
    0.39
     Senator
    0.39
     kid
    0.39
     ALL
    0.39
    POSITIVE LOGITS
     природы
    0.53
    ви
    0.49
     மூலம்
    0.49
     onun
    0.49
     природе
    0.48
    тере
    0.47
    сер
    0.47
    ли
    0.46
    ાસ
    0.46
    чув
    0.46
    Act Density 0.001%

    No Known Activations