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

    Neuronpedia

    INDEX
    Explanations

    androidx compose coroutines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    1.38
     Fiber
    1.34
    a
    1.30
     Hanford
    1.22
     Levant
    1.21
    ם
    1.20
    ص
    1.20
    ی
    1.19
    ism
    1.18
    h
    1.17
    POSITIVE LOGITS
    uğu
    1.18
    ังสือ
    1.13
    ਰ
    1.11
    すすめ
    1.09
    ності
    1.09
    ljeni
    1.04
     téléphonique
    1.03
    uée
    1.02
    ੀ
    1.02
    াট
    1.00
    Act Density 0.001%

    No Known Activations