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

    Neuronpedia

    INDEX
    Explanations

    interest rates and finance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Пор
    0.50
     відповід
    0.47
    nika
    0.45
     अड्
    0.45
     प्रमुख
    0.43
     угро
    0.43
     нор
    0.43
     সুযোগ
    0.43
    нік
    0.43
    वाणी
    0.42
    POSITIVE LOGITS
     for
    0.51
     maximizes
    0.45
    و
    0.44
     Really
    0.43
     पॉलिटी
    0.42
    ល់
    0.42
     vraiment
    0.42
     Deliver
    0.42
     deliver
    0.41
    реи
    0.41
    Act Density 0.001%

    No Known Activations