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

    Neuronpedia

    INDEX
    Explanations

    foreign words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    un
    0.56
    is
    0.53
    로
    0.53
    髹
    0.52
    ab
    0.51
    Новости
    0.51
    us
    0.50
    лен
    0.48
    an
    0.47
    าง
    0.47
    POSITIVE LOGITS
     എല്ലാവ
    0.49
     সত্য
    0.48
     වැඩ
    0.47
     verstär
    0.47
     抗
    0.46
     lavoro
    0.46
     ong
    0.45
     সে
    0.45
     因為
    0.44
     ত
    0.44
    Act Density 0.000%

    No Known Activations