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

    Neuronpedia

    INDEX
    Explanations

    create or using objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    गेटिव
    0.53
    𝘸
    0.49
    ंचित
    0.47
     Coatings
    0.47
     occasione
    0.47
     Tories
    0.47
     Workshops
    0.46
    <unused53>
    0.46
    ઙ
    0.46
    стых
    0.46
    POSITIVE LOGITS
    を使
    0.52
     usando
    0.52
     create
    0.51
    を使用して
    0.51
     system
    0.50
    setup
    0.50
    を使用
    0.50
     using
    0.50
     crear
    0.50
     utiliser
    0.50
    Act Density 0.012%

    No Known Activations