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

    Neuronpedia

    INDEX
    Explanations

    Russian localities

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “Oblast” (the Russian administrative‐division term).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ertas
    -0.07
    udiantes
    -0.07
     teenage
    -0.07
     út
    -0.06
    iddet
    -0.06
    /dialog
    -0.06
     ance
    -0.06
    Semantic
    -0.06
     GMT
    -0.06
     dried
    -0.06
    POSITIVE LOGITS
    isObject
    0.07
    GRAPH
    0.07
     "}↵
    0.06
     Clem
    0.06
    UIStoryboardSegue
    0.06
     honeymoon
    0.06
    navigate
    0.06
    kits
    0.06
    ्थ
    0.06
     thoughtful
    0.06
    Act Density 0.002%

    No Known Activations