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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yourself
    0.70
    was
    0.64
    我覺得
    0.57
     నాకు
    0.57
     तुमने
    0.57
     Yourself
    0.56
    your
    0.55
     приходит
    0.55
     எனக்கு
    0.54
    feels
    0.54
    POSITIVE LOGITS
     ourselves
    1.20
     можем
    1.18
     хотим
    1.09
     داریم
    0.98
     будем
    0.98
     pouvons
    0.98
    ಿದ್ದೇವೆ
    0.94
     знаем
    0.93
     છીએ
    0.93
    avons
    0.91
    Act Density 0.345%

    No Known Activations