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

    Neuronpedia

    INDEX
    Explanations

    changed state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     येतात
    0.64
     می‌شوند
    0.56
     होतात
    0.55
     करतात
    0.53
     जातात
    0.52
     सांगतात
    0.52
    ходят
    0.51
     येतो
    0.50
     येते
    0.50
    します
    0.50
    POSITIVE LOGITS
     became
    0.83
     came
    0.82
     gave
    0.82
     took
    0.80
     did
    0.79
     was
    0.78
     went
    0.77
     began
    0.76
     grew
    0.73
     fell
    0.72
    Act Density 0.128%

    No Known Activations