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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .nr
    -0.06
    Foundation
    -0.06
    泣
    -0.06
     dwar
    -0.06
    many
    -0.06
     Smooth
    -0.06
    Click
    -0.06
    stack
    -0.06
     Year
    -0.06
    ných
    -0.06
    POSITIVE LOGITS
     jewish
    0.07
     Telegraph
    0.07
     민주
    0.06
    quia
    0.06
     ціл
    0.06
     disposed
    0.06
     sparking
    0.06
    */↵↵↵
    0.06
    .sql
    0.06
     Тур
    0.06
    Act Density 0.027%

    No Known Activations