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

    Neuronpedia

    INDEX
    Explanations

    code inside parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stratej
    -0.07
    /sweetalert
    -0.06
     Telerik
    -0.06
    州
    -0.06
    ;?>"
    -0.06
     Egypt
    -0.06
    ):
    -0.06
     kultur
    -0.06
    -Headers
    -0.06
     sliders
    -0.06
    POSITIVE LOGITS
    ического
    0.07
    (DIS
    0.07
    Var
    0.07
    gons
    0.07
     enquanto
    0.07
    -Pack
    0.06
    {}↵
    0.06
     Printer
    0.06
     ascending
    0.06
    hotel
    0.06
    Act Density 0.008%

    No Known Activations