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

    Neuronpedia

    INDEX
    Explanations

    Mad Libs Generator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дый
    0.47
     ସ
    0.46
     Schauspieler
    0.46
     besonder
    0.46
    ](./
    0.46
     δὲ
    0.45
    Quadrant
    0.45
    siehe
    0.45
    ழ்பெற்ற
    0.45
     изменение
    0.44
    POSITIVE LOGITS
    n
    0.54
     politically
    0.52
    ,
    0.50
    ;
    0.48
     dollars
    0.47
     Flour
    0.47
     wines
    0.46
    のが
    0.46
     waves
    0.45
     expenditures
    0.45
    Act Density 0.004%

    No Known Activations