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

    Neuronpedia

    INDEX
    Explanations

    code and dataframes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Trademark
    -0.07
     burdens
    -0.06
     nurturing
    -0.06
    ,get
    -0.06
    -DD
    -0.06
     procurement
    -0.06
    .af
    -0.06
     Tango
    -0.06
    央
    -0.06
    -social
    -0.06
    POSITIVE LOGITS
    nginx
    0.08
     *[
    0.07
     vlády
    0.07
     chết
    0.06
     yüzyıl
    0.06
    .basic
    0.06
    .getStyle
    0.06
     Informationen
    0.06
     cuerpo
    0.06
    った
    0.06
    Act Density 0.025%

    No Known Activations