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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     также
    1.02
    overall
    1.01
     نیز
    1.00
     ise
    0.95
     également
    0.93
     أيضًا
    0.91
    较为
    0.91
     inoltre
    0.91
    示例
    0.90
    additional
    0.89
    POSITIVE LOGITS
     And
    2.18
     But
    1.82
    And
    1.57
     That
    1.44
     Or
    1.40
     Và
    1.38
     Not
    1.37
     Like
    1.33
     Nhưng
    1.28
     Maybe
    1.27
    Act Density 0.571%

    No Known Activations