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

    Neuronpedia

    INDEX
    Explanations

    geography and compression flags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Бы
    0.95
    طق
    0.88
    𝗻
    0.82
    ilio
    0.82
     seus
    0.81
     உள்ளிட்ட
    0.81
    ものの
    0.80
     awọn
    0.79
    ության
    0.79
     fios
    0.79
    POSITIVE LOGITS
    ER
    0.88
    ต่ำ
    0.86
    EM
    0.86
    ليه
    0.86
    IM
    0.83
    ക്കായി
    0.83
    ساز
    0.82
    ties
    0.82
    Zespół
    0.80
    recv
    0.79
    Act Density 0.001%

    No Known Activations