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

    Neuronpedia

    INDEX
    Explanations

    sentence beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ัน
    1.05
    жные
    1.04
    senha
    1.02
     одежды
    1.01
     comerciantes
    1.00
    Acknowledgments
    0.99
     artículos
    0.98
     ADMINISTRATIVE
    0.98
    議員
    0.96
    נים
    0.96
    POSITIVE LOGITS
     (>
    0.92
     (
    0.91
     gains
    0.90
     dramatically
    0.90
    ia
    0.88
     through
    0.88
    er
    0.85
    çada
    0.83
     my
    0.82
     signific
    0.82
    Act Density 0.592%

    No Known Activations