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

    Neuronpedia

    INDEX
    Explanations

    common prefixes and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.54
     būt
    1.39
     utiliser
    1.37
    без
    1.34
    <0x80>
    1.33
     இல்லாத
    1.31
     be
    1.30
     skincare
    1.29
     doesn
    1.28
     ikke
    1.27
    POSITIVE LOGITS
    -{\
    1.54
    iš
    1.32
    ia
    1.19
     birthplace
    1.17
     meagre
    1.16
     puis
    1.16
     말미암
    1.14
     tuvieron
    1.14
    هان
    1.11
     hitherto
    1.10
    Act Density 0.019%

    No Known Activations