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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of specific countries or legal jurisdictions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Idx
    -0.06
     electrical
    -0.06
    /bg
    -0.06
     Flores
    -0.06
     타이
    -0.05
     SERIAL
    -0.05
    Slides
    -0.05
     died
    -0.05
     trilogy
    -0.05
     Ý
    -0.05
    POSITIVE LOGITS
    에서
    0.07
    ????
    0.07
    .every
    0.07
    Studies
    0.06
    .getSelection
    0.06
    .transforms
    0.06
    AVOR
    0.06
    !"
    0.06
    했습니다
    0.06
     intuit
    0.06
    Act Density 0.033%

    No Known Activations