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

    Neuronpedia

    INDEX
    Explanations

    phrase compound nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ത്തിയ
    0.34
    綏
    0.33
    aecat
    0.33
     சிறி
    0.32
    DrvGPIO
    0.31
     veines
    0.31
     النبي
    0.31
    詡
    0.31
     BVHTree
    0.31
    爍
    0.31
    POSITIVE LOGITS
    <0xC2>
    0.45
    <eos>
    0.35
      
    0.35
    ...
    0.33
     or
    0.33
    </em>
    0.32
    <0xE3>
    0.31
     ,
    0.31
     ​​
    0.31
     “
    0.30
    Act Density 0.306%

    No Known Activations