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

    Neuronpedia

    INDEX
    Explanations

    updating screen, quality rating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     무엇
    0.26
     artériel
    0.25
    ник
    0.24
     NavBar
    0.23
    مان
    0.23
    вери
    0.23
    ihull
    0.23
    い
    0.23
    𝘢
    0.23
    товано
    0.22
    POSITIVE LOGITS
    0
    0.39
    ۰
    0.39
    :
    0.39
    q
    0.37
    ;
    0.35
    ᱐
    0.34
    ០
    0.34
    the
    0.33
    us
    0.32
    ၀၀
    0.32
    Act Density 3.462%

    No Known Activations