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

    Neuronpedia

    INDEX
    Explanations

    Gemma team at Google DeepMind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    0.36
     Перейти
    0.35
    LetterIndex
    0.35
    érir
    0.33
     പദ്ധതി
    0.33
    getTable
    0.33
    Tabpage
    0.33
    elect
    0.33
    𝒍
    0.32
    </i>
    0.31
    POSITIVE LOGITS
    에요
    0.43
     -
    0.41
     ľudí
    0.39
    いです
    0.37
     včetně
    0.37
     kirjo
    0.37
     including
    0.36
     Estudos
    0.36
     👋
    0.36
    apj
    0.35
    Act Density 0.036%

    No Known Activations