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

    Neuronpedia

    INDEX
    Explanations

    last or other word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    बाट
    0.51
     multifunctional
    0.50
    ită
    0.48
    đi
    0.47
     కార్య
    0.46
     αυτο
    0.46
    ளா
    0.46
     डिलिव
    0.46
     върху
    0.45
     motore
    0.45
    POSITIVE LOGITS
    ";
    0.50
    0.49
        
    0.48
    ;"
    0.46
    "));
    0.46
    ;
    0.45
       
    0.44
    薮
    0.44
    ,"
    0.43
          
    0.43
    Act Density 0.003%

    No Known Activations