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

    Neuronpedia

    INDEX
    Explanations

    communication and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ếm
    0.50
     intrusive
    0.46
     wary
    0.41
     प्रशिक्षण
    0.41
    鹑
    0.41
     പരിശീല
    0.41
    ới
    0.40
    WithFieldContext
    0.40
     caviar
    0.39
    ्रेंस
    0.39
    POSITIVE LOGITS
    (
    0.51
    سی
    0.49
     fondamentali
    0.46
    이라고
    0.45
     ਮੰ
    0.43
    ים
    0.42
    olom
    0.42
    ኵ
    0.42
    Saat
    0.41
    Windows
    0.40
    Act Density 0.002%

    No Known Activations