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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on Polish-language word pieces—especially tokens containing Polish diacritics (ą, ć, ł, ś, etc.)—i.e. it flags Polish text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .ExecuteReader
    -0.07
     دارند
    -0.06
     Ann
    -0.06
    ाहन
    -0.06
    _encoding
    -0.06
    Money
    -0.06
     использу
    -0.06
    C
    -0.06
     داده
    -0.06
    ];
↵
↵
    -0.06
    POSITIVE LOGITS
    ões
    0.07
    änger
    0.07
     billions
    0.07
    σμός
    0.07
    ão
    0.07
     vibrant
    0.06
     Meter
    0.06
    cisi
    0.06
     roleId
    0.06
    bugs
    0.06
    Act Density 0.378%

    No Known Activations