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

    Neuronpedia

    INDEX
    Explanations

    reopening after lockdowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     வக
    0.41
    тый
    0.40
     معلومات
    0.40
     ذاتی
    0.40
    Logical
    0.39
     aplica
    0.38
     Intelligen
    0.38
     Intelli
    0.38
     wiki
    0.37
     akun
    0.37
    POSITIVE LOGITS
     normalcy
    1.08
     normality
    1.03
     lockdowns
    0.92
    正常
    0.86
     commutes
    0.82
     restrictions
    0.82
     норма
    0.81
     NORMAL
    0.79
    restrictions
    0.77
    NORMAL
    0.76
    Act Density 0.006%

    No Known Activations