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

    Neuronpedia

    INDEX
    Explanations

    attribution after "from"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flannel
    0.43
     রচিত
    0.40
    CAN
    0.40
    ܓ
    0.37
     subtleties
    0.37
     cadence
    0.37
     cowboy
    0.36
    🐓
    0.36
     formalism
    0.35
     crappy
    0.35
    POSITIVE LOGITS
     Rahul
    0.41
    himanyu
    0.39
     मीडिया
    0.38
    岁的
    0.38
    ्म
    0.37
    สื่อ
    0.37
    ньої
    0.37
    炲
    0.37
    껑
    0.37
     Rohit
    0.36
    Act Density 0.000%

    No Known Activations