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

    Neuronpedia

    INDEX
    Explanations

    for years,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ARE
    1.26
     летом
    1.20
     millones
    1.18
    ıyla
    1.16
    ی
    1.15
    ME
    1.06
    ことにより
    1.06
     voorkomen
    1.05
    KE
    1.05
     wiederum
    1.04
    POSITIVE LOGITS
    س
    1.31
    ს
    1.21
    ك
    1.20
    ાઈ
    1.20
    ्स
    1.19
     וש
    1.16
    ін
    1.14
    רים
    1.06
    მ
    1.06
     Individuals
    1.05
    Act Density 0.004%

    No Known Activations