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

    Neuronpedia

    INDEX
    Explanations

    Roosevelt ran, hornet, tournaments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сравни
    0.53
     ಏಕೆಂದರೆ
    0.52
    ισμό
    0.51
     証明
    0.50
    नोट
    0.49
     உம்
    0.48
     इंजीनियरिंग
    0.48
     porówn
    0.48
    réal
    0.47
    સી
    0.47
    POSITIVE LOGITS
     eg
    0.44
     sco
    0.43
    ,
    0.42
     prof
    0.41
     ly
    0.41
     id
    0.41
     vo
    0.41
     ev
    0.40
     rin
    0.40
     lst
    0.40
    Act Density 0.003%

    No Known Activations