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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    generic
    -0.06
    -0.06
    neighbor
    -0.06
    iks
    -0.06
     Blanch
    -0.06
     náklad
    -0.06
    bles
    -0.06
     bel
    -0.06
    /svg
    -0.06
     其
    -0.06
    POSITIVE LOGITS
    大利
    0.07
     düzenli
    0.06
    (socket
    0.06
    (od
    0.06
    休
    0.06
     Мат
    0.06
    (options
    0.06
    шибка
    0.06
    „M
    0.06
     Poke
    0.06
    Act Density 0.055%

    No Known Activations