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

    Neuronpedia

    INDEX
    Explanations

    professional decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     слегка
    0.41
    Wenn
    0.36
    ༠
    0.36
    ཎ
    0.35
     약간
    0.34
     থাকিলেও
    0.34
    焼
    0.34
    निम्नलिखित
    0.34
    疑似
    0.33
     เพิ่ม
    0.33
    POSITIVE LOGITS
     naš
    0.33
     undoubtedly
    0.33
    ↵
    0.32
     sådan
    0.32
     our
    0.32
      
    0.31
     ourselves
    0.30
     [
    0.30
     certainly
    0.30
     continue
    0.29
    Act Density 0.073%

    No Known Activations