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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alumno
    -0.07
    도가
    -0.06
     зни
    -0.06
     SECTION
    -0.06
     христи
    -0.06
    引き
    -0.06
    osomes
    -0.06
    _el
    -0.06
    aro
    -0.06
     automobiles
    -0.06
    POSITIVE LOGITS
     slun
    0.07
    -क
    0.07
    nc
    0.07
    fel
    0.07
     Lov
    0.06
    -pt
    0.06
     Rockefeller
    0.06
     blok
    0.06
    _IOC
    0.06
    ocumented
    0.06
    Act Density 0.003%

    No Known Activations