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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шили
    -0.07
    enzhen
    -0.06
    Act
    -0.06
     önlem
    -0.06
    Im
    -0.06
    CreateInfo
    -0.06
     підприємств
    -0.06
     Ronaldo
    -0.06
    .Threading
    -0.06
    ्पर
    -0.06
    POSITIVE LOGITS
     scramble
    0.07
    PTS
    0.06
    ovaná
    0.06
     ид
    0.06
     strive
    0.06
    ДА
    0.06
    готов
    0.06
    ."+
    0.06
    /↵↵↵
    0.06
    */↵↵↵
    0.06
    Act Density 0.005%

    No Known Activations