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

    Neuronpedia

    INDEX
    Explanations

    conjunctions in various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     takže
    0.88
     είναι
    0.82
     で
    0.81
     dari
    0.77
     pentru
    0.77
     Pentru
    0.75
     例如
    0.74
     sebagainya
    0.73
     untuk
    0.72
     plays
    0.72
    POSITIVE LOGITS
    และ
    3.14
     and
    2.98
     ও
    2.94
     ਅਤੇ
    2.88
     и
    2.86
     અને
    2.86
     आणि
    2.80
     và
    2.78
     ಮತ್ತು
    2.77
     और
    2.75
    Act Density 3.102%

    No Known Activations