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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonché
    0.64
     maupun
    0.61
    прочем
    0.54
     quoique
    0.50
    及
    0.50
     एवं
    0.49
     sowie
    0.49
     sekä
    0.47
     odnosno
    0.45
    及び
    0.45
    POSITIVE LOGITS
    했고
    1.47
     And
    1.45
    And
    1.42
     และ
    1.34
    었고
    1.30
     ហើយ
    1.30
     거고
    1.27
     iar
    1.27
     있고
    1.11
    이고
    1.06
    Act Density 0.663%

    No Known Activations