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
     trails
    -0.08
     exports
    -0.07
     Names
    -0.07
     applause
    -0.07
     NGOs
    -0.07
    @Inject
    -0.06
    Dirs
    -0.06
     NAMES
    -0.06
     bev
    -0.06
    ;|
    -0.06
    POSITIVE LOGITS
    践
    0.07
    =sub
    0.07
    พวกเข
    0.06
    ład
    0.06
     labeled
    0.06
    ади
    0.06
    324
    0.06
     устройства
    0.06
    =logging
    0.06
     className
    0.06
    Act Density 0.024%

    No Known Activations