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

    Neuronpedia

    INDEX
    Explanations

    specific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    世界的
    0.39
     British
    0.39
     alloying
    0.38
     Australian
    0.37
     untold
    0.37
     குறிப்பாக
    0.35
     royalties
    0.35
     bungalow
    0.35
     Into
    0.34
     resulta
    0.34
    POSITIVE LOGITS
    which
    0.57
     ซึ่ง
    0.52
    と呼ばれる
    0.47
    。
    0.47
    ซึ่ง
    0.46
     which
    0.46
     или
    0.44
    .
    0.42
     appunto
    0.42
    ',
    0.41
    Act Density 0.266%

    No Known Activations