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

    Neuronpedia

    INDEX
    Explanations

    your schema or pirate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attendant
    0.69
     whe
    0.68
     لي
    0.67
     been
    0.67
    もちろん
    0.66
     וכ
    0.64
    ти
    0.63
     कुछ
    0.62
     ná
    0.62
     〢
    0.60
    POSITIVE LOGITS
    人员
    0.77
    t
    0.68
     sparsim
    0.67
    getBy
    0.67
    formerly
    0.66
    ‍♀️
    0.64
     partidas
    0.64
    నకు
    0.64
     Grüße
    0.62
     graphique
    0.61
    Act Density 0.578%

    No Known Activations