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

    Neuronpedia

    INDEX
    Explanations

    called, termed, known as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Contains
    0.41
    ంతో
    0.40
    ceding
    0.40
    Consentiti
    0.36
     ඉක්
    0.36
     परेशानी
    0.35
    ۂ
    0.35
    اتے
    0.35
    কাতে
    0.35
    Delay
    0.34
    POSITIVE LOGITS
     called
    1.61
    called
    1.34
     Called
    1.30
     termed
    1.28
    叫做
    1.28
     llamado
    1.27
     bernama
    1.26
     nazy
    1.25
    稱為
    1.24
     называ
    1.23
    Act Density 0.383%

    No Known Activations