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

    Neuronpedia

    INDEX
    Explanations

    mixed language or translations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    1.01
    क्शन
    0.98
    𝐡
    0.96
    İŞ
    0.95
    м
    0.94
     शिका
    0.92
     l
    0.92
    暴
    0.90
    ını
    0.90
    еру
    0.89
    POSITIVE LOGITS
     Тем
    1.29
     হইবার
    1.25
     Josephine
    1.23
     Biodiversity
    1.23
    Наи
    1.19
     Chairperson
    1.19
     Nir
    1.18
     буду
    1.18
    testAvg
    1.17
     Нико
    1.17
    Act Density 0.001%

    No Known Activations