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

    Neuronpedia

    INDEX
    Explanations

    code identifiers and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     then
    -1.13
     them
    -0.96
    They
    -0.94
    他們
    -0.94
    Hvorfor
    -0.90
    addListener
    -0.90
    Penulis
    -0.88
    Hvordan
    -0.88
    onsors
    -0.88
    他们
    -0.85
    POSITIVE LOGITS
     ilyen
    0.91
    無し
    0.86
    albeit
    0.86
     ==>
    0.86
    こんなに
    0.85
    吭
    0.82
     данного
    0.82
    鄒
    0.81
     mijne
    0.81
    却被
    0.79
    Act Density 0.018%

    No Known Activations