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

    Neuronpedia

    INDEX
    Explanations

    document formatting and recipes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inches
    0.49
    Indiana
    0.45
     inches
    0.43
    वायरमेंट
    0.42
    onać
    0.41
     centimetres
    0.41
     लर्न
    0.40
    imsu
    0.40
    ése
    0.39
    преде
    0.38
    POSITIVE LOGITS
     VL
    0.42
     Z
    0.41
     Flex
    0.39
     vasodil
    0.39
     soph
    0.39
     Sh
    0.38
    iii
    0.38
     WA
    0.38
     klaus
    0.37
     clar
    0.37
    Act Density 0.002%

    No Known Activations