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

    Neuronpedia

    INDEX
    Explanations

    public opinion and trust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    带宽
    0.49
     luscious
    0.48
    Calcium
    0.47
    手动
    0.46
     succulent
    0.46
     kasut
    0.46
     ছবির
    0.45
     사용
    0.45
     cyst
    0.44
    计算
    0.44
    POSITIVE LOGITS
     unpopular
    0.67
     perceptions
    0.61
     воспринима
    0.57
     patriotism
    0.55
    polls
    0.55
    headlines
    0.54
     favorables
    0.53
     pessimism
    0.53
     mistrust
    0.52
    perception
    0.52
    Act Density 0.029%

    No Known Activations