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

    Neuronpedia

    INDEX
    Explanations

    capital cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reached
    -0.08
     acre
    -0.08
    ····
    -0.08
    ENSOR
    -0.07
    .setY
    -0.07
    --,
    -0.07
    =Y
    -0.07
     libertine
    -0.06
    -two
    -0.06
     Immediate
    -0.06
    POSITIVE LOGITS
    昭和
    0.07
    絵
    0.07
     Release
    0.06
    、『
    0.06
     дорож
    0.06
     insanlar
    0.06
    ’ın
    0.06
     ngOnDestroy
    0.06
    })(
    0.06
    、
    0.05
    Act Density 0.022%

    No Known Activations