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

    Neuronpedia

    INDEX
    Explanations

    problem constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Љ
    0.36
    اصل
    0.34
    ایط
    0.33
     مطلوب
    0.33
     Kaleidoscope
    0.33
     Apartment
    0.32
    जफ्
    0.32
     coral
    0.31
     elbows
    0.31
    Smiling
    0.31
    POSITIVE LOGITS
    Constraints
    0.39
    提示
    0.37
     объяс
    0.35
     restrain
    0.34
     Совет
    0.34
     Constraints
    0.34
     விளக்கம்
    0.34
    нді
    0.33
     constraint
    0.33
    我們可以
    0.33
    Act Density 0.005%

    No Known Activations