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

    Neuronpedia

    INDEX
    Explanations

    academic subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ness
    1.37
    ம்
    1.26
    াধিকার
    1.24
    ها
    1.20
    ed
    1.14
    ة
    1.13
    ς
    1.12
    ों
    1.11
    nesses
    1.10
    🏼
    1.08
    POSITIVE LOGITS
    ally
    1.77
    ically
    1.46
    ALLY
    1.43
    ዊ
    1.28
    álním
    1.22
    િયલ
    1.18
    ческим
    1.17
     lst
    1.15
    ज्ञ
    1.14
    álny
    1.13
    Act Density 0.316%

    No Known Activations