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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ry
    -0.07
     Photography
    -0.06
    十二
    -0.06
     SUN
    -0.06
    /met
    -0.06
     Ryu
    -0.06
    画像
    -0.06
    .Preference
    -0.06
    (Tile
    -0.06
    (TIM
    -0.06
    POSITIVE LOGITS
    каж
    0.08
     chuyển
    0.07
     gelir
    0.07
     newPos
    0.06
     bulletin
    0.06
    Failure
    0.06
    lasyon
    0.06
     ödem
    0.06
    �
    0.06
    ipl
    0.06
    Act Density 0.007%

    No Known Activations