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

    Neuronpedia

    INDEX
    Explanations

    full articles and official websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jaro
    0.51
    感を
    0.51
    estado
    0.47
     интеллектуа
    0.47
    ʼn
    0.47
    yl
    0.46
    orsky
    0.46
    非常
    0.46
    enson
    0.45
     intellectually
    0.45
    POSITIVE LOGITS
     przede
    0.43
    chandise
    0.42
     Ergebnisse
    0.41
     간단
    0.41
     Trouvez
    0.41
     Solving
    0.41
     Ending
    0.40
    зок
    0.40
    Buildings
    0.40
     Buildings
    0.39
    Act Density 0.003%

    No Known Activations