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

    Neuronpedia

    INDEX
    Explanations

    country names/codes

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of sovereign country names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     spouse
    -0.07
    сього
    -0.07
     Axios
    -0.07
    idunt
    -0.07
     başta
    -0.06
     zaman
    -0.06
    �
    -0.06
    Capture
    -0.06
    firm
    -0.06
    voie
    -0.06
    POSITIVE LOGITS
    _big
    0.07
     '');↵
    0.06
     cloves
    0.06
     cran
    0.06
     PERF
    0.06
    Cases
    0.06
    ｀ヽ
    0.06
    ＼↵
    0.06
     xmlns
    0.06
    acağım
    0.06
    Act Density 0.023%

    No Known Activations