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

    Neuronpedia

    INDEX
    Explanations

    write or tell something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    非常に
    1.06
     indivíduos
    0.99
     oldukça
    0.99
     بسیار
    0.97
     매우
    0.94
     অত্যন্ত
    0.91
     상당히
    0.90
     경우가
    0.87
     केवळ
    0.87
     значительно
    0.86
    POSITIVE LOGITS
     some
    1.89
     five
    1.54
     Some
    1.53
    some
    1.46
    Some
    1.39
     me
    1.38
     ten
    1.35
     another
    1.35
     cinco
    1.34
     några
    1.33
    Act Density 0.855%

    No Known Activations