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

    Neuronpedia

    INDEX
    Explanations

    constantly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ihr
    1.70
    Mét
    1.45
    Så
    1.44
    ème
    1.43
    அ
    1.43
    baixo
    1.42
    daftar
    1.40
    ash
    1.39
     povos
    1.38
     montaña
    1.38
    POSITIVE LOGITS
    ка
    1.68
    ა
    1.36
    ,
    1.35
    т
    1.29
    ли
    1.27
    ，
    1.25
    но
    1.22
     Anders
    1.21
     Premiere
    1.20
    一些
    1.19
    Act Density 0.750%

    No Known Activations