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

    Neuronpedia

    INDEX
    Explanations

    [noun] of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     其中
    0.38
     historically
    0.37
    することは
    0.36
     ሌ
    0.36
    これは
    0.36
     ねえ
    0.35
    শিক
    0.34
     хороший
    0.34
     طويل
    0.34
    គ្នា
    0.34
    POSITIVE LOGITS
     của
    1.31
     ofthe
    1.27
     của
    1.23
    ของ
    1.16
    ofthe
    1.16
     της
    1.11
     του
    1.08
    OfThe
    1.05
     של
    1.01
     of
    1.00
    Act Density 0.008%

    No Known Activations