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

    Neuronpedia

    INDEX
    Explanations

    identified

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edor
    -0.06
     beş
    -0.06
     Peninsula
    -0.06
     οργ
    -0.06
    Toy
    -0.06
                ↵            ↵
    -0.06
    _players
    -0.06
     صورت
    -0.06
     Diğer
    -0.06
    رق
    -0.06
    POSITIVE LOGITS
     kittens
    0.07
    .ins
    0.06
    атем
    0.06
     ping
    0.06
     Geb
    0.06
    *:
    0.06
    Outlet
    0.06
    >$
    0.06
     #[
    0.06
     torrent
    0.06
    Act Density 0.044%

    No Known Activations