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

    Neuronpedia

    INDEX
    Explanations

    levels and democratic elections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bali
    0.45
     Belong
    0.40
     convain
    0.40
    كا
    0.39
     diduga
    0.39
     Крим
    0.39
    ညီ
    0.38
     Botswana
    0.38
     Eritrea
    0.38
    هلاك
    0.38
    POSITIVE LOGITS
    Then
    0.50
    ter
    0.44
    Neben
    0.43
     beginners
    0.42
    Nope
    0.42
    Window
    0.40
    นะนำ
    0.40
    January
    0.40
    Quién
    0.39
    然后
    0.39
    Act Density 0.005%

    No Known Activations