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

    Neuronpedia

    INDEX
    Explanations

    former roles and professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    目前
    0.58
    т
    0.49
     currently
    0.48
    on
    0.47
     vengono
    0.46
     Currently
    0.45
     actuelle
    0.45
     attualmente
    0.45
    ам
    0.45
    后
    0.45
    POSITIVE LOGITS
     ehemaligen
    0.71
     býval
    0.69
    舊
    0.64
    former
    0.61
    formerly
    0.61
     autrefois
    0.60
     ehemalige
    0.58
     former
    0.57
    Former
    0.56
     Former
    0.54
    Act Density 0.025%

    No Known Activations