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

    Neuronpedia

    INDEX
    Explanations

    Became or began

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     असतो
    0.73
     असते
    0.70
     يكون
    0.68
     असतात
    0.66
     იქნება
    0.64
     থাকে
    0.60
     ہوتی
    0.59
     होती
    0.59
     izango
    0.57
     sẽ
    0.56
    POSITIVE LOGITS
     became
    1.65
    became
    1.55
     began
    1.35
     blev
    1.33
     came
    1.31
     Became
    1.23
     went
    1.17
     kellett
    1.17
     took
    1.14
     стала
    1.14
    Act Density 0.023%

    No Known Activations