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

    Neuronpedia

    INDEX
    Explanations

    AI GD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     described
    0.43
     CHO
    0.41
     do
    0.40
     Cho
    0.40
     significance
    0.40
     নিত
    0.40
     funkci
    0.40
     রেজ
    0.39
     file
    0.38
     самому
    0.38
    POSITIVE LOGITS
    polls
    0.48
    મ્
    0.47
     florals
    0.47
    antoms
    0.45
     intérieure
    0.45
    mind
    0.45
     pastries
    0.44
     rookies
    0.43
    ల్లు
    0.43
     poppies
    0.43
    Act Density 0.000%

    No Known Activations