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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    申博
    -0.07
    ých
    -0.06
    /******************************************************************************↵
    -0.06
    лих
    -0.06
    uş
    -0.06
    oru
    -0.06
     щось
    -0.06
     OMIT
    -0.06
     одного
    -0.06
     emphasizes
    -0.06
    POSITIVE LOGITS
     clk
    0.07
     Dre
    0.07
     nós
    0.07
     енерг
    0.07
     коллек
    0.06
    akt
    0.06
     wre
    0.06
    ้↵
    0.06
    lated
    0.06
     kav
    0.06
    Act Density 0.005%

    No Known Activations