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

    Neuronpedia

    INDEX
    Explanations

    lists in different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.47
    0.46
    ना
    0.43
    Organizer
    0.39
     uncountable
    0.39
    करणा
    0.38
     pe
    0.38
     flights
    0.38
     Hallmark
    0.38
     Collins
    0.38
    POSITIVE LOGITS
     zupeł
    0.52
     permettent
    0.48
    àn
    0.47
    ó
    0.46
     amelyet
    0.46
     ஆகியவை
    0.45
     နှစ်
    0.45
     ។
    0.45
    的可
    0.45
    🛀
    0.45
    Act Density 0.003%

    No Known Activations