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

    Neuronpedia

    INDEX
    Explanations

    recommendation contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    и
    1.25
    вых
    1.21
    нансо
    1.20
     filo
    1.16
    зок
    1.12
     karya
    1.10
     wollen
    1.09
     annoncé
    1.08
     Ihrer
    1.06
    От
    1.03
    POSITIVE LOGITS
    lly
    1.26
     drawable
    1.22
    twenty
    1.20
     seconded
    1.20
     vantage
    1.19
     siting
    1.19
     खासा
    1.18
     щодо
    1.18
    Alternatively
    1.18
    ection
    1.17
    Act Density 0.105%

    No Known Activations